CN115623131A - Shunting system based on voice customer service - Google Patents
Shunting system based on voice customer service Download PDFInfo
- Publication number
- CN115623131A CN115623131A CN202211381857.3A CN202211381857A CN115623131A CN 115623131 A CN115623131 A CN 115623131A CN 202211381857 A CN202211381857 A CN 202211381857A CN 115623131 A CN115623131 A CN 115623131A
- Authority
- CN
- China
- Prior art keywords
- data
- customer service
- data set
- demand
- 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.)
- Granted
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
- H04M3/50—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
- H04M3/5232—Call distribution algorithms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the field of data processing, in particular to a voice customer service-based distribution system, which is characterized in that a data storage module, a data receiving module, a switching module, a data processing module and a data support module are arranged to classify received demand requests, the optimal processing category of each customer service end is determined, when the demand requests are received, a demander provides brief consultation contents, the received consultation contents are converted into text information, a switching mode is adjusted according to the text information, the demand requests are distributed to the customer service end with the highest efficiency for processing the type of demand requests, the demand requests are accurately classified, and a specific matching mode is used for matching the customer service end with the highest processing efficiency, so that the service processing efficiency is improved, the flow rate of the customer service system is increased, meanwhile, a database is accurately called in the process of solving the consultation and answering of the customer service, data support is provided, customer service is assisted, the service processing efficiency is improved, and the service efficiency of the whole customer service system is further improved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a flow distribution system based on voice customer service analysis.
Background
The customer service system plays an important role in the production and management activities of enterprises, is a service window closely connecting the enterprises and users, plays a very important role in product sale, after-sales service, technical support, consultation and complaint, and has a large burden on the customer service system of the enterprises with large service volume and large coverage, so that the arrangement of the customer service distribution system is particularly important for improving the customer service answering efficiency;
chinese patent publication No.: CN111556208A discloses a method and a device for customer service online switching, and relates to the technical field of customer service systems. Wherein, the method comprises the following steps: distributing remote customer service for a customer accessing a customer service system and transferring the remote customer service to the remote customer service; when determining that the service performed by the client relates to an operation service, determining an agent service corresponding to the operation service; and the remote customer service is connected to the seat customer service so that the seat customer service processes the operation service. By using the method, the shunting of the service of the call center site can be realized.
However, the prior art has the following problems,
1. the consultation contents of the demand end are not briefly known by a technical means and then distributed, and different consultation requirements are automatically distributed to the customer service end familiar with the type of service so as to improve the customer service operation efficiency;
for application scenes with wider service range, the requirements for service personnel are more severe, and a system for automatically extracting keywords and pushing related data to the service personnel to support by analyzing voice information is lacked in the prior art.
Disclosure of Invention
In order to solve the above problems, the present invention provides a flow distribution system based on voice customer service analysis, including:
the system comprises a data storage module, a data processing module and a data processing module, wherein a plurality of data sets are stored in the data storage module, any data set comprises common information and a plurality of keywords, the keywords are different from one another, and the data storage module determines the association level among the data sets;
the data receiving module is used for receiving a demand request sent by a demand end and consultation contents corresponding to the demand request;
the switching module is used for switching the requirement request to the customer service end for processing;
the data processing module is connected with the data storage module, the data receiving module and the switching module and completes data exchange, and after receiving the data of the data receiving module, the data processing module classifies the demand requests, calls the processed demand request data records of each customer service end and determines the optimal processing category of each customer service end and the data set related to each customer service end;
the data processing module converts the consultation content into text information, extracts keywords in the text information, judges a data set matched with the text information, judges whether distribution calculation is carried out or not, randomly transfers the demand request to a current non-busy line customer service end when the distribution calculation is not carried out, and determines a transfer mode according to the association level of the data set matched with the text information and the associated data set of the non-busy line customer service end when the distribution calculation is required;
and the data support module is connected with the data storage module, extracts voice data during the communication of the customer service end, judges a data set matched with the voice data, and transmits the data set to the customer service end.
Further, the data storage module determines the correlation level among the data sets, wherein the data storage module extracts keywords in the data sets and calculates the correlation coefficient K among the data sets according to the following formula,
wherein, E represents the coincidence quantity of the keywords in the two data sets, E0 represents the total quantity of the keywords in the two data sets, N represents the difference value of the quantity of the keywords in the two data sets, N0 represents the preset keyword quantity difference parameter, P0 represents the data total quantity of the two data sets, and alpha represents the conversion coefficient.
Furthermore, a first incidence relation contrast parameter K1 and a second incidence relation contrast parameter K2 are preset in the data storage module, the data storage module compares the incidence relation coefficient K corresponding to the data sets with the correlation coefficients K1 and K2 to determine the correlation level between the data sets, wherein,
when K is larger than or equal to K2, the data storage module judges that the data sets are in a first association grade;
when K1 is more than or equal to K and less than K2, the data storage module judges that the data sets are in a second association grade;
and when K is less than K1, the data storage module judges that the data sets have a third correlation grade.
Further, when the data receiving module receives a demand request of a demand party, the data receiving module prompts the demand party to send consultation content, and after the consultation content is converted into text information, the data receiving module extracts keywords in the text information and records the keywords to a demand keyword data set; the data processing module determines a set of data that matches the demand request, wherein,
and when the incidence relation coefficient K between a demand keyword data set generated by text information of the consultation content corresponding to the demand request and any data set in the data storage module is more than or equal to K3, the data processing module judges that the demand request is matched with the data set, wherein K3 is a third incidence relation comparison parameter, and K3 is more than K2.
Further, when the data processing module determines a data set matched with the demand request, and when an association relation coefficient K of a demand keyword data set generated by a plurality of data sets and text information of consultation content corresponding to the demand request in the data storage module is greater than or equal to K3, selecting the data set with the maximum association relation coefficient K with the demand keyword data set as a matched data set of the demand request.
Further, a sample number parameter R is preset in the data processing module, and when the data receiving module receives a demand request, it sends information to the data processing module, and the data processing module determines whether to perform allocation calculation, wherein,
when the number of the switched demand requests is smaller than the preset sample number parameter R, the data processing module judges that distribution calculation is not carried out, the demand requests are switched to a currently not-busy line customer service end at random, and after the customer service end finishes processing the demand requests, time length information T of the customer service end for processing the demand requests is recorded;
and when the number of the switched demand requests is more than or equal to the preset sample number parameter R, the data processing module judges that distribution calculation is required.
Further, the data processing module determines an optimal processing category of each customer service end, wherein the data processing module calls a data record of the processed demand requests of each customer service end and classifies the demand requests, the data processing module is internally provided with a corresponding relation between a data set and a category, different data sets correspond to different categories, the demand requests are classified according to the corresponding relation, the average duration delta T of the customer service end for processing the demand requests of each category is calculated and sequenced, the category of the demand request with the shortest average duration is used as the optimal processing category of the customer service end, and the data processing module marks the association between the customer service end and the data set corresponding to the demand request with the shortest average duration.
Further, the data processing module judges that distribution calculation is needed, and determines a switching mode according to the data set matched with the text information, wherein the data set matched with the text information corresponding to the consultation content of the demand request is determined, the data set is marked, the demand request is classified according to the marked data set, the category of the demand request is determined, and the demand request is switched to a customer service end with the optimal processing category as the category;
and when the optimal processing type is that all the customer service terminals of the type are busy, the data processing module determines a data set associated with the remaining customer service terminals which are not busy, judges the association level of the marking data set and the data set, and determines a switching mode,
if a data set with a first association level of the marked data set exists, the data processing module calls a history record of all customer service end processing demand requests associated with the data set, calculates the average time length delta T of all the customer service ends for processing the category demand requests corresponding to the marked data set, and switches the demand requests to the customer service end with the minimum average time length delta T required for processing the category demand requests;
if a data set with a second association level of the marked data set exists, the data processing module transfers the demand request to any customer service end associated with the data set;
and if the association level of the data set associated with the remaining non-busy line customer service terminals and the association level of the marked data set are both a third association level, the data processing module forwards the demand request to any customer service terminal in the remaining non-busy line customer service terminals.
Further, the common information includes data, and after the data set is transmitted to the customer service end, the display device of the customer service end acquires and displays the data.
Further, when the data support module judges the data set matched with the voice data, the voice data is converted into text information, keywords in the text information are extracted, the keywords are recorded into a voice data set, an incidence relation coefficient K between the voice data set and the data set in the data storage module is calculated, when K is larger than or equal to K0, the data processing module judges that the voice data is matched with the data set, and K0 represents a preset voice matching coefficient.
Compared with the prior art, the method and the system have the advantages that through the arrangement of the data storage module, the data receiving module, the switching module, the data processing module and the data support module, the received demand requests are classified to call processed demand request data records of all customer service ends, the optimal processing category of all customer service ends is determined, when the demand requests are received, a demander provides brief consultation contents, the received consultation contents are converted into text information, keywords in the text information are extracted, a data set matched with the text information is judged, the switching mode is determined according to the association level of the data set matched with the text information and the associated data set of the customer service ends which are not busy, the demand requests are distributed to the customer service end with the highest processing efficiency of the type of demand requests, the demand requests are classified accurately and matched to the customer service end with the highest processing efficiency in a specific matching mode, the business processing efficiency is improved, the flow rate of a customer service system is increased, and meanwhile, a database is called accurately in the customer service consultation process, data support is provided, the customer service is assisted, the business processing efficiency is improved, and the business processing efficiency is further improved.
Particularly, the data storage module is provided with a plurality of data sets, the data sets can be increased or decreased according to the service fields needing to provide the consultation service in actual conditions, the data sets and the associated keywords are established for different service fields, so that the services of corresponding types can be accurately identified and distributed in the consultation distribution process, the consultation types of the demand side can be effectively represented in the keyword comparison mode, the distribution reliability and the data identification precision of the system are improved, and the misallocation is avoided.
Particularly, the data receiving module is arranged to receive the demand request of the demand party, meanwhile, the demand party can provide brief consultation content when sending the demand request, the consultation content can be voice or text, the association degree calculation is carried out on the keywords and the preset data set on the basis of the speech, the association relation coefficient K is calculated, the association relation coefficient K has good representation on the association of the data set, the data set matched with the consultation content is determined, and then the demand request is classified.
Particularly, the invention records the data of each client processing demand request by setting a preset sample quantity parameter R, the system automatically counts data for the previous R times of switching, determines which type of demand request is more skillful to process by the client, in the practical situation, for a customer service system with wider service scope, customer service personnel accurately master all consultation knowledge, each customer service end has different speed and efficiency for processing each service, the system carries out automatic data statistics on the data, further determines the demand request type with highest processing efficiency at each customer service end, establishes the incidence relation between the demand request type and a data set, facilitates the subsequent flow distribution calculation and identification, distributes the corresponding type of demand request to the customer service end with highest processing efficiency, and further improves the customer service processing efficiency.
Particularly, the invention sets the association level between the data sets, when the service is busy, the current demand request is distributed to the customer service end with higher processing communication according to the association level of the remaining un-connected customer service end association data set and the current mark data set, and different association levels correspond to different switching methods.
Particularly, the data support module is arranged, and data information related to conversation contents is accurately extracted from the database by extracting keywords in the voice conversation process between the customer service and the demand side and is transmitted to the customer service side for displaying, so that the operation of customer service personnel is reduced, the data calculation accuracy is accurate, the customer service personnel are assisted, and the customer service efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a voice customer service analysis-based distribution system according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a data structure of a data set according to an embodiment of the present invention.
In the figure, 1: and (4) data collection.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described in conjunction with the following examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and do not delimit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1, which is a diagram of a voice customer service analysis-based distribution system according to an embodiment of the present invention, the voice customer service analysis-based distribution system of the present invention includes,
the data storage module is internally stored with a plurality of data sets, for any data set, the data set comprises common information and a plurality of keywords, the keywords are different, and the data storage module determines the association level among the data sets;
the data receiving module is used for receiving a demand request sent by a demand end and consultation contents corresponding to the demand request;
the switching module is used for switching the requirement request to the customer service end for processing;
the data processing module is connected with the data storage module, the data receiving module and the switching module and completes data exchange, and after receiving the data of the data receiving module, the data processing module classifies the demand requests, calls the processed demand request data records of each customer service terminal and determines the optimal processing category of each customer service terminal and the data set associated with each customer service terminal;
the data processing module converts the consultation content into text information, extracts keywords in the text information, judges a data set matched with the text information, judges whether distribution calculation is carried out or not, randomly switches the demand request to a current busy line customer service terminal when the distribution calculation is not carried out, and determines a switching mode according to the association level of the data set matched with the text information and the data set associated with the busy line customer service terminal when the distribution calculation is carried out;
and the data support module is connected with the data storage module, extracts voice data during the communication of the customer service end, judges a data set matched with the voice data, and transmits the data set to the customer service end.
Specifically, for the setting of the data set, the setting can be modified according to the range of the specific consulting services, the specific form of the data set is not limited, one data set and corresponding support data are set for each type of service, and keywords pre-corresponding to service association are selected to establish association with the data set.
Specifically, referring to fig. 2, the data storage module determines the association level between the data sets, wherein the data storage module extracts keywords in the data sets and calculates an association coefficient K between the data sets according to the following formula,
wherein E represents the coincidence quantity of keywords in the two data sets, E0 represents the total quantity of the keywords in the two data sets, N represents the difference value of the quantity of the keywords in the two data sets, N0 represents a preset keyword quantity difference parameter, P0 represents the total quantity of the data in the two data sets, and alpha represents a conversion coefficient.
Specifically, a first incidence relation contrast parameter K1 and a second incidence relation contrast parameter K2 are preset in the data storage module, the data storage module compares the incidence relation coefficient K corresponding to the data sets with K1 and K2 to determine the incidence level between the data sets, wherein,
when K is larger than or equal to K2, the data storage module judges that the data sets are in a first association grade;
when K1 is more than or equal to K and less than K2, the data storage module judges that the data sets are in a second association grade;
and when K is less than K1, the data storage module judges that the data sets have a third correlation grade.
Specifically, the data storage module is provided with a plurality of data sets, the data sets can be increased or decreased according to the business fields needing to provide the consultation service in practical situations, the data sets and the associated keywords related to the different business fields are established for different business fields, so that the corresponding types of businesses can be accurately identified in the consultation distribution process for distribution, the consultation types of the demanders can be effectively represented in a keyword comparison mode, the reliability and the data identification precision of system distribution are improved, and misallocation is avoided.
Specifically, when the data receiving module receives a demand request of a demand party, the data receiving module prompts the demand party to send consultation content, and after the consultation content is converted into text information, the data receiving module extracts keywords in the text information and records the keywords to a demand keyword data set; the data processing module determines a set of data that matches the demand request, wherein,
and when the association relation coefficient K between a demand keyword data set generated by text information of the consultation content corresponding to the demand request and any data set in the data storage module is more than or equal to K3, the data processing module judges that the demand request is matched with the data set, wherein K3 is a third association relation comparison parameter, and K3 is more than K2.
Specifically, the consultation content may be in a voice form or a text form, after the demander sends a demand request, the data receiving module sends a prompt to the terminal of the demander, and the demander can input voice or input text information on the terminal of the demander and send the voice or text information to the data receiving module.
Specifically, when the data processing module determines a data set matched with the demand request, and when an association coefficient K of a demand keyword data set generated by a plurality of data sets and text information of consultation content corresponding to the demand request in the data storage module is greater than or equal to K3, the data set with the maximum association coefficient K with the demand keyword data set is selected as a matched data set of the demand request.
Specifically, a data receiving module is arranged to receive a demand request of a demand party, the demand party can provide brief consultation content when sending the demand request, the consultation content can be voice or text, keywords and a preset data set are extracted on the basis of the speech to calculate the association degree, an association relation coefficient K is calculated, the association relation coefficient K has good representation on the association of the data set, the data set matched with the consultation content is determined, and the demand request is classified.
Specifically, a sample number parameter R is preset in the data processing module, and when the data receiving module receives a request, information is sent to the data processing module, and the data processing module determines whether to perform allocation calculation, wherein,
when the number of the switched demand requests is smaller than the preset sample number parameter R, the data processing module judges that distribution calculation is not carried out, the demand requests are switched to a current customer service end which is not busy, and after the customer service end finishes processing the demand requests, the time length information T of the customer service end for processing the demand requests is recorded;
and when the number of the switched demand requests is more than or equal to the preset sample number parameter R, the data processing module judges that distribution calculation is required.
Specifically, a preset sample quantity parameter R is set, data of each client for processing a demand request is recorded, the system automatically counts data for the previous R times of switching, and determines which type of demand request is more skillful to process by the client.
Specifically, the data processing module determines an optimal processing category of each customer service end, wherein the data processing module calls a data record of a processed demand request of each customer service end and classifies the demand request, a corresponding relation between a data set and a category is preset in the data processing module, different data sets correspond to different categories, the demand requests are classified according to the corresponding relation, the average time length delta T of the customer service end for processing the demand requests of each category is calculated and sequenced, the category of the demand request with the shortest average time length is used as the optimal processing category of the customer service end, and the data set association of the customer service end and the demand request with the shortest average time length is marked.
Specifically, the data processing module judges that distribution calculation is needed, and determines a switching mode according to the data set matched with the text information, wherein the data set matched with the text information corresponding to the consultation content of the demand request is determined, the data set is marked, the demand request is classified according to the marked data set, the category of the demand request is determined, and the demand request is switched to a customer service end with the optimal processing category as the category;
and when the optimal processing type is that all the customer service terminals of the type are busy, the data processing module determines a data set associated with the remaining customer service terminals which are not busy, judges the association level of the marking data set and the data set, and determines a switching mode,
if a data set with a first association level as the association level of the marked data set exists, the data processing module calls a history record of all customer service terminals associated with the data set to process demand requests, calculates the average time length delta T of all the customer service terminals for processing the type demand requests corresponding to the marked data set, and transfers the demand requests to the customer service terminals with the minimum average time length delta T required for processing the type demand requests;
if a data set with a second association level of the marked data set exists, the data processing module transfers the demand request to any customer service end associated with the data set;
and if the association level of the data set associated with the remaining non-busy line customer service terminals and the association level of the marked data set are both a third association level, the data processing module forwards the demand request to any customer service terminal in the remaining non-busy line customer service terminals.
Specifically, the invention sets the association level among the data sets, when the service is busy, the current demand request is distributed to the customer service end with higher processing communication according to the association level of the remaining un-connected customer service end association data set and the current mark data set, different association levels correspond to different switching methods, in the practical situation, the number of the customer service ends which are good at a certain demand request is reduced along with the increase of proficiency, therefore, different switching methods are needed to be adopted for different association levels, for example, for the second association level data set, a switching mode of random distribution is adopted, the demand request is dispersed, centralized distribution to a certain customer service ends is avoided, the load is avoided being overlarge, and the service efficiency of the customer service system is further integrally improved.
Specifically, the common information includes data, and after the data set is transmitted to the customer service end, the display device of the customer service end acquires and displays the data.
Specifically, when the data support module judges the data set matched with the voice data, the voice data is converted into text information, keywords in the text information are extracted, the keywords are recorded into the voice data set, an association relation coefficient K between the voice data set and the data set in the data storage module is calculated, when K is larger than or equal to K0, the data processing module judges that the voice data is matched with the data set, and K0 represents a preset voice matching coefficient.
Specifically, the data support module is arranged, and data information related to conversation content is accurately extracted from the database by extracting keywords in the voice conversation process between the customer service and the demand side and is transmitted to the customer service side for display, so that the operation of customer service personnel is reduced, the data calculation accuracy is accurate, the customer service personnel are assisted, and the customer service business efficiency is improved.
Specifically, for the extraction of text keywords, which is a mature prior art, there are various extraction methods, and the present invention does not limit the extraction methods.
Specifically, the specific structures and connection modes of the data storage module, the data receiving module, the switching module, the data processing module and the data support module are not limited, and the data storage module, the data processing module and the data support module are mature prior art, the data storage module only needs to be provided with a database capable of being called and stored and a data processing unit, the data receiving module only needs to be connected with a cloud end to receive information sent by a user end, the switching module is a data transfer platform and only needs to complete call switching and data switching, the data processing module only needs to complete data processing and data interaction, and the data support module only needs to complete data processing and data interaction.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. A voice customer service based distribution system, comprising:
the data storage module is internally stored with a plurality of data sets, for any data set, the data set comprises common information and a plurality of keywords, the keywords are different, and the data storage module determines the association level among the data sets;
the data receiving module is used for receiving a demand request sent by a demand end and consultation contents corresponding to the demand request;
the switching module is used for switching the requirement request to the customer service end for processing;
the data processing module is connected with the data storage module, the data receiving module and the switching module and completes data exchange, and after receiving the data of the data receiving module, the data processing module classifies the demand requests, calls the processed demand request data records of each customer service terminal and determines the optimal processing category of each customer service terminal and the data set associated with each customer service terminal;
the data processing module converts the consultation content into text information, extracts keywords in the text information, judges a data set matched with the text information, judges whether distribution calculation is carried out or not, randomly transfers the demand request to a current non-busy line customer service end when the distribution calculation is not carried out, and determines a transfer mode according to the association level of the data set matched with the text information and the associated data set of the non-busy line customer service end when the distribution calculation is required;
and the data support module is connected with the data storage module, extracts voice data during the communication of the customer service end, judges a data set matched with the voice data, and transmits the data set to the customer service end.
2. The voice customer service-based distribution system according to claim 1, wherein the data storage module determines a correlation level between each data set, wherein the data storage module extracts keywords in each data set and calculates a correlation coefficient K between the data sets according to the following formula,
wherein E represents the coincidence quantity of keywords in the two data sets, E0 represents the total quantity of the keywords in the two data sets, N represents the difference value of the quantity of the keywords in the two data sets, N0 represents a preset keyword quantity difference parameter, P0 represents the total quantity of the data in the two data sets, and alpha represents a conversion coefficient.
3. The voice customer service-based distribution system according to claim 2, wherein a first correlation comparison parameter K1 and a second correlation comparison parameter K2 are preset in the data storage module, the data storage module compares the correlation coefficient K corresponding to the data sets with K1 and K2 to determine the correlation level between the data sets, wherein,
when K is more than or equal to K2, the data storage module judges that the data sets have a first association grade;
when K1 is more than or equal to K and less than K2, the data storage module judges that the data sets are in a second association grade;
and when K is less than K1, the data storage module judges that the data sets have a third correlation level.
4. The voice customer service-based distribution system according to claim 3, wherein the data receiving module prompts a demander to send out a consultation content when receiving a demand request from the demander, and after converting the consultation content into text information, the data receiving module extracts keywords in the text information and records the keywords into a demand keyword data set; the data processing module determines a set of data that matches the demand request, wherein,
and when the association relation coefficient K between a demand keyword data set generated by text information of the consultation content corresponding to the demand request and any data set in the data storage module is more than or equal to K3, the data processing module judges that the demand request is matched with the data set, wherein K3 is a third association relation comparison parameter, and K3 is more than K2.
5. The voice customer service-based distribution system according to claim 4, wherein when the data processing module determines a data set matching the demand request, and when an association coefficient K between a plurality of data sets in the data storage module and a demand keyword data set generated from text information of a consultation content corresponding to the demand request is greater than or equal to K3, the data set with the maximum association coefficient K with the demand keyword data set is selected as the matching data set of the demand request.
6. The voice customer service-based distribution system according to claim 5, wherein a sample number parameter R is preset in the data processing module, and when the data receiving module receives a request, the data receiving module sends a message to the data processing module, and the data processing module determines whether to perform distribution calculation, wherein,
when the number of the switched demand requests is smaller than the preset sample number parameter R, the data processing module judges that distribution calculation is not carried out, the demand requests are switched to a currently not-busy line customer service end at random, and after the customer service end finishes processing the demand requests, time length information T of the customer service end for processing the demand requests is recorded;
and when the number of the switched demand requests is more than or equal to the preset sample number parameter R, the data processing module judges that allocation calculation is required.
7. The voice customer service based distribution system according to claim 6, wherein the data processing module determines an optimal processing category of each customer service end, wherein the data processing module invokes a data record of the processed demand requests of each customer service end to classify the demand requests, wherein the data processing module is configured to preset a correspondence between data sets and categories, different data sets correspond to different categories, classify the demand requests according to the correspondence, calculate an average duration Δ T for the customer service end to process the demand requests of each category, sort the average duration Δ T, use the category of the demand request with the shortest average duration as the optimal processing category of the customer service end, and mark the customer service end in association with the data set corresponding to the demand request with the shortest average duration.
8. The voice customer service-based distribution system according to claim 7, wherein the data processing module determines that distribution calculation is required, and determines a switching manner according to the data set matched with the text information, wherein a data set matched with the text information corresponding to the consultation content of the demand request is determined, the data set is marked, the demand request is classified according to the marked data set, the category of the demand request is determined, and the demand request is switched to a customer service terminal whose optimal processing category is the category;
and when the optimal processing type is that all the customer service terminals of the type are busy, the data processing module determines a data set associated with the remaining customer service terminals which are not busy, judges the association level of the marking data set and the data set, and determines a switching mode,
if a data set with a first association level of the marked data set exists, the data processing module calls a history record of all customer service end processing demand requests associated with the data set, calculates the average time length delta T of all the customer service ends for processing the category demand requests corresponding to the marked data set, and switches the demand requests to the customer service end with the minimum average time length delta T required for processing the category demand requests;
if a data set with a second association level of the association level with the marked data set exists, the data processing module transfers the demand request to any customer service end associated with the data set;
and if the association level of the data set associated with the rest of the un-busy line customer service terminals and the association level of the marked data set are a third association level, the data processing module transfers the demand request to any customer service terminal in the rest of the un-busy line customer service terminals.
9. The voice customer service based distribution system according to claim 1, wherein the general information includes data, and after the data set is transmitted to the customer service end, a display device of the customer service end obtains and displays the data.
10. The voice customer service-based distribution system according to claim 1, wherein when the data support module determines the data set matched with the voice data, the voice data is converted into text information, keywords in the text information are extracted, the keywords are recorded in the voice data set, an association coefficient K between the voice data set and the data set in the data storage module is calculated, when K is greater than or equal to K0, the data processing module determines that the voice data is matched with the data set, and K0 represents a preset voice matching coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211381857.3A CN115623131B (en) | 2022-11-07 | 2022-11-07 | Shunt system based on voice customer service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211381857.3A CN115623131B (en) | 2022-11-07 | 2022-11-07 | Shunt system based on voice customer service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115623131A true CN115623131A (en) | 2023-01-17 |
| CN115623131B CN115623131B (en) | 2023-04-28 |
Family
ID=84878351
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211381857.3A Active CN115623131B (en) | 2022-11-07 | 2022-11-07 | Shunt system based on voice customer service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115623131B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040486A (en) * | 2018-08-30 | 2018-12-18 | 中通天鸿（北京）通信科技股份有限公司 | A kind of position system of call center |
| CN109040484A (en) * | 2018-07-16 | 2018-12-18 | 安徽信尔联信息科技有限公司 | A kind of Auto-matching contact staff method |
| CN111932144A (en) * | 2020-08-25 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Customer service seat allocation method, customer service seat allocation device, server and storage medium |
| CN112615968A (en) * | 2019-12-05 | 2021-04-06 | 商客通尚景科技（上海）股份有限公司 | Shunting method and device for cloud call center telephone |
| US20220239777A1 (en) * | 2021-01-27 | 2022-07-28 | Dell Products L.P. | Assigning customer calls to customer care agents based on compatability |
-
2022
- 2022-11-07 CN CN202211381857.3A patent/CN115623131B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109040484A (en) * | 2018-07-16 | 2018-12-18 | 安徽信尔联信息科技有限公司 | A kind of Auto-matching contact staff method |
| CN109040486A (en) * | 2018-08-30 | 2018-12-18 | 中通天鸿（北京）通信科技股份有限公司 | A kind of position system of call center |
| CN112615968A (en) * | 2019-12-05 | 2021-04-06 | 商客通尚景科技（上海）股份有限公司 | Shunting method and device for cloud call center telephone |
| CN111932144A (en) * | 2020-08-25 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Customer service seat allocation method, customer service seat allocation device, server and storage medium |
| US20220239777A1 (en) * | 2021-01-27 | 2022-07-28 | Dell Products L.P. | Assigning customer calls to customer care agents based on compatability |
Non-Patent Citations (1)
| Title |
|---|
| 任虹林: "四川移动公司农经信息呼叫系统的设计与实现" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115623131B (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20080019493A1 (en) | Telecommunication services reporting system | |
| CN109978608A (en) | The marketing label analysis extracting method and system of target user's portrait | |
| CN110445942A (en) | A kind of outer paging system of intelligence and intelligent calling-out method | |
| KR102163081B1 (en) | Interactive voice bot server and unmanned counsel system | |
| KR101975320B1 (en) | Method and System For Providing Call Center Sharing Service Based On Big Data and Artificial Intelligence | |
| CN112367434B (en) | Automatic distribution system for power grid customer service operation resources | |
| CN112734185A (en) | Intelligent queuing scheduling method | |
| US6813349B2 (en) | Communication of user data to an automatic call distributor agent | |
| US20020196929A1 (en) | Enhanced agent automatic call distribution Control | |
| CN106572273A (en) | Matching system of user incoming call access customer service line and method thereof | |
| CN112801676A (en) | Express industry call center service method, device, equipment and system | |
| CN115623131A (en) | Shunting system based on voice customer service | |
| US20080080683A1 (en) | Operation-related information management device,method, program and telephone operation management system | |
| CN115623130B (en) | Agent conversation service business distribution method and system | |
| JP3210926B2 (en) | Communication service control system and method | |
| CN116340482A (en) | Multi-skill customer service auxiliary product based on enterprise WeChat combined with NLP engine | |
| CN116189346A (en) | Intelligent queuing and calling system for digital science and technology deep integration hall management and marketing scene | |
| CN112634510B (en) | Intelligent queuing system for online business handling | |
| EP2469823B1 (en) | Computer telecommunication integration exchanger (ctiex), system and method for channel associated data transmission of agent and automatic service | |
| CN105592234B (en) | Processing method of communication data and device | |
| CN103516917B (en) | Internet information treating method and apparatus | |
| KR100751204B1 (en) | System and method for analyzing voice quality per mobile communication service subscriber | |
| JP2003348241A (en) | Method for receiving call and call receiving program | |
| CN116980522B (en) | System and method for notifying customer image based on intelligent quality inspection | |
| CN115412510B (en) | Flexible configuration method based on distributed framework service |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230413 Address after: 530013 No. 6, Minzhu Road, Xingning District, Nanning City, Guangxi Zhuang Autonomous Region Applicant after: GUANGXI POWER GRID Co.,Ltd. Address before: No. 372, 3rd floor, building 8, No. 663, Tianhe North Road, Tianhe District, Guangzhou, Guangdong 510000 Applicant before: Guangdong Yuantao Enterprise Management Consulting Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |