CN110475032A - Multi-service interface switching method, device, computer installation and storage medium - Google Patents
Multi-service interface switching method, device, computer installation and storage medium Download PDFInfo
- Publication number
- CN110475032A CN110475032A CN201910578491.0A CN201910578491A CN110475032A CN 110475032 A CN110475032 A CN 110475032A CN 201910578491 A CN201910578491 A CN 201910578491A CN 110475032 A CN110475032 A CN 110475032A
- Authority
- CN
- China
- Prior art keywords
- incoming call
- contact staff
- service
- customer
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
-
- 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
- H04M3/5175—Call or contact centers supervision 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
- H04M3/51—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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Abstract
The present invention provides a kind of multi-service interface switching method, device, computer installation and computer readable storage medium.The multi-service interface switching method includes: the customer data that incoming call client is obtained according to the phone information of access；The customer service demand of the incoming call client is predicted according to the customer data, and the customer service demand of prediction is presented to the contact staff for docking the incoming call client；The voice communication between the incoming call client and the contact staff is monitored, and obtains the voice content between the incoming call client and the contact staff；Text conversion is carried out to the voice content and extracts an at least keyword from the text after conversion；Operation system interface of the current business changing interface for the integrated service system that the contact staff is logged in extremely with an at least keyword match for the extraction.The present invention relates to Business Process Optimizing technology, it can be achieved that improving the working efficiency and customer satisfaction of contact staff.
Description
Technical field
The present invention relates to field of communication technology more particularly to a kind of multi-service interface switching methods, device, computer installation
And computer readable storage medium.
Background technique
Larger enterprise is generally owned by artificial customer service team, is mainly responsible for and collects client feedback, answer client consults
Inquiry, customer in response complaint etc..The service quality of customer service team is directly related to client's public praise an of enterprise, the client of record
The formulation fed back also for product improvement, enterprise development plan has an important influence.Current customer service system not smart enoughization,
Customer service can not learn client's demand before answering customer phone in advance, in inquiry business need between multiple operation systems into
Row switching, inefficiency.
Summary of the invention
In view of above-mentioned, the present invention provides a kind of multi-service interface switching method, device, computer installation and computer-readable
Storage medium can be improved the working efficiency of contact staff, improve customer satisfaction.
One embodiment of the application provides a kind of multi-service interface switching method, which comprises
When having telephone access, the customer data of incoming call client is obtained according to the phone information of access；
The customer service demand of the incoming call client is predicted according to the customer data, and the customer service demand of prediction is presented to pair
Meet the contact staff of the incoming call client；
Monitor it is described incoming call client and the contact staff between voice communication, and obtain the incoming call client with it is described
Voice content between contact staff；
Text conversion is carried out to the voice content and extracts an at least keyword from the text after conversion；And
The current business changing interface for the integrated service system that the contact staff is logged in the extraction at least
The operation system interface of one keyword match.
Preferably, the integrated service system integration has multiple operation systems, described to be obtained according to the phone information of access
Before the step of customer data of incoming call client further include:
Data pick-up operation is carried out to the database of each operation system, and is cleaned obtained data are extracted
Operation, to filter the data for not meeting preset requirement；
Data after cleaning are subjected to data conversion, and the data after conversion process are determined according to preset data model
The table structure of justice is fitted into the tables of data of a total Database；And
It develops to obtain the integrated service system based on the total Database.
Preferably, it is also wrapped after the step of customer service demand that the incoming call client is predicted according to the customer data
It includes:
It determines that art guides document if matching with the customer service demand of the prediction, and words art guide document is presented to
The contact staff.
Preferably, described that text conversion is carried out to the voice content and extracts at least one key from the text after conversion
The step of word includes:
Text conversion carried out to the voice content, and based on the customer service demand of TF-IDF algorithm and the prediction from conversion
An at least keyword is extracted in text afterwards.
Preferably, it is also wrapped after the step of voice content obtained between the incoming call client and the contact staff
It includes:
Customer service voices are extracted from the voice content, and Emotion identification is carried out to the customer service voices, it is described to obtain
The Emotion identification result of contact staff；And
When the Emotion identification result is unhealthy emotion, exports default mood and guide content to the contact staff.
Preferably, described that customer service voices are extracted from the voice content, and Emotion identification is carried out to the customer service voices,
To include: the step of obtaining the Emotion identification result of the contact staff
It is established according to multiple voice sample datas and trains to obtain an Emotion identification model；
The mostly described voice content carries out noise reduction, cutting and role and identifies operation, to extract the customer service voices；And
The customer service voices are input to the Emotion identification model, to obtain the Emotion identification knot of the contact staff
Fruit.
Preferably, the multi-service interface switching method further include:
Text and at least one crucial word analysis after being converted according to the voice obtain the incoming call of the incoming call client
Reason；And
The work order classification for determining the incoming call reason, by service work order information typing work order of the contact staff point
Under class；
Wherein, the service work order information includes at least incoming call customer information, contact staff's information, incoming call reason.
One embodiment of the application provides a kind of multi-service changing interface device, and described device includes:
Data obtains module, for obtaining the client of incoming call client according to the phone information of access when having telephone access
Data；
Prediction module, for predicting the customer service demand of the incoming call client according to the customer data, and by the visitor of prediction
The demand of clothes is presented to the contact staff for docking the incoming call client；
Voice obtains module, for monitoring the voice communication between the incoming call client and the contact staff, and obtains
Voice content between the incoming call client and the contact staff；
Extraction module, for carrying out text conversion to the voice content and extracting at least one pass from the text after conversion
Key word；And
Switching module, the current business changing interface of the integrated service system for logging in the contact staff to institute
State the operation system interface of an at least keyword match for extraction.
One embodiment of the application provides a kind of computer installation, and the computer installation includes processor and memory,
Several computer programs are stored on the memory, the processor is for when executing the computer program stored in memory
The step of realizing multi-service interface switching method as elucidated before.
One embodiment of the application provides a kind of computer readable storage medium, is stored thereon with computer program, described
The step of multi-service interface switching method as elucidated before is realized when computer program is executed by processor.
Above-mentioned multi-service interface switching method, device, computer installation and computer readable storage medium, according to access
Phone information can look-ahead incoming call client customer service demand, can preferably for send a telegram here client counseling services are provided, connect in phone
After logical, analyzed in real time using speech recognition technology and convert call voice as call text, realize related industry to grab keyword
Be engaged in system interface automatic switchover, while in dialog procedure real-time monitoring contact staff speech, mood, and according to monitoring tie
Properly art guidance is pacified with mood to contact staff for fruit push, can also be according to the call content of text and key after conversion
Word carries out intelligent classification to the incoming call reason of this incoming call client, and carries out customer service work order automatic input, improves contact staff
Order efficiency and customer service and client both sides usage experience.
Detailed description of the invention
It, below will be to required in embodiment description in order to illustrate more clearly of the technical solution of embodiment of the present invention
The attached drawing used is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the step flow chart of multi-service interface switching method in one embodiment of the invention.
Fig. 2 is the step flow chart of multi-service interface switching method in another embodiment of the present invention.
Fig. 3 is the functional block diagram of multi-service changing interface device in one embodiment of the invention.
Fig. 4 is computer schematic device in one embodiment of the invention.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying mode, the present invention will be described in detail.It should be noted that in the absence of conflict, presently filed embodiment and reality
The feature applied in mode can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment
Only some embodiments of the invention, rather than whole embodiments.Based on the embodiment in the present invention, this field
Those of ordinary skill's every other embodiment obtained without making creative work, belongs to guarantor of the present invention
The range of shield.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Preferably, multi-service interface switching method of the invention is applied in one or more computer installation.It is described
Computer installation be it is a kind of can according to the instruction for being previously set or store, automatic progress numerical value calculating and/or information processing
Equipment, hardware include but is not limited to microprocessor, specific integrated circuit (Application Specific Integrated
Circuit, ASIC), programmable gate array (Field-Programmable Gate Array, FPGA), digital processing unit
(Digital Signal Processor, DSP), embedded device etc..
The computer installation can be the meter such as desktop PC, laptop, tablet computer, server, mobile phone
Calculate equipment.The computer installation can with user by the modes such as keyboard, mouse, remote controler, touch tablet or voice-operated device into
Row human-computer interaction.
Embodiment one:
Fig. 1 is the step flow chart of multi-service interface switching method preferred embodiment of the present invention.Institute according to different requirements,
The sequence for stating step in flow chart can change, and certain steps can be omitted.
As shown in fig.1, the multi-service interface switching method specifically includes following steps.
Step S11, when having telephone access, the customer data of incoming call client is obtained according to the phone information of access.
In one embodiment, before answering the call, contact staff can according to itself account password or face characteristic or
Vocal print feature logs in integrated service system, which is a customer service system, and can polymerize has existing multiple business
The data of system, when the customer service demand for needing to meet incoming call client carries out data query, contact staff is not necessarily to multiple
It is switched between operation system, customer service efficiency can be improved.
In one embodiment, the database data of multiple operation systems can be integrated by structure together by ETL technology
Build a total Database.Specifically, it can use ETL tool and extract data from each database to a middle layer, to extraction
Data carry out cleaning operation, undesirable data filtering is fallen, such as wrong data, deficiency of data, repeat number
According to etc., then the data progress data conversion of cleaning, for example carry out unification (title, template, standard, computation rule etc. of format
Carry out unification), the combination of data/field segmentation or calculate, finally by the data set after conversion process according to predetermined physical
The table structure of data model definitions is fitted into the tables of data of total Database.Integrated service system is developed in front end based on the total Database
System, the integrated service system integration have the function of original multiple operation systems, and contact staff can be by logging in the integrated industry
Business system carries out data query.
When having telephone access, the customer data of incoming call client can be obtained according to the phone information of access.The total data
Library stores customer profile, includes, but are not limited to, the identity data of client (such as ID card No., gender, birthday, connection electricity
Words, address etc.), buying or used commodity or the data of service, (such as declaration form number, declaration form content, financial products, finance are borrowed
Loan, settlement of insurance claim service etc.), consumer record (such as date, place, means of payment etc.), activation record (such as application Claims Resolution
Deng), the information such as customer service system contact record (such as customer complaint, consulting).For example, the customer data may include insurer
Essential information, declaration form number, premium content, beneficiary's information, payment situation, Claims Resolution record etc..
In one embodiment, the devices such as fixed-line telephone, mobile phone, smart watch access visitor can be used in incoming call client
Dress system establishes the session with contact staff.The customer data further includes incoming call client when accessing customer service system, according to
Intelligent voice system guides the customer information of input or the Demand and service information of selection.For example, incoming call client can be by phone
Virtual key (such as number 0-9, # key, * key etc.) input customer information, including but not limited to ID card No., the date of birth,
Declaration form number, product serial number, service password etc..
Step S12, the customer service demand of the incoming call client is predicted according to the customer data, and by the customer service demand of prediction
It is presented to the contact staff for docking the incoming call client.
In one embodiment, the customer data can be analyzed according to default algorithm, to predict the incoming call
The customer service demand of client, the default algorithm can be bayesian algorithm, decision Tree algorithms etc..For example, can use decision
Tree algorithm is analyzed to incoming call client's business datum handled recently, the business information that will expire, business arrearage information etc.
Predict the customer service demand of incoming call client.When the user that sends a telegram here accesses the customer service system, the connection date is that client's premium is withholdd
In the front and back 10 days on date, can be predicted the user customer service demand may be paid with premium it is related.It can be by the client of prediction
Demand is shown in the currently used display equipment (such as computer screen) of contact staff.
In one embodiment, displaying customer portrait, and the client that will be drawn can also be drawn according to the customer data
Portrait is shown in the display equipment.
It in one embodiment, can be according to the customer service need after prediction obtains the customer service demand of the incoming call client
Art guides document if asking determination matched, and words art guide document is presented to the contact staff.Due to each
Contact staff's communication capability is different, especially for contact staff recently, guides, purely relies on personal if lacking standard words art
When experience is linked up, communication effectiveness, efficiency may be undesirable, therefore can be exported according to the customer service demand of the prediction default
It talks about art and guides document, and guide document to be presented to the contact staff the default words art.
It should be understood that can pre-establish multiple words arts guides document, not each words art guides document to establish label,
And then it can determine that art guides text with the customer service demand best match of prediction according to customer service demand and the matching degree of label
Shelves.
In one embodiment, when the phone of the incoming call client is switched on, art is talked about for the versatility of early period, it can be with
Broadcasted by presetting the sound of contact staff that incoming call client is currently docked in speech synthesis system synthesis, contact staff without
It all repeats to say when need to receive calls every time primary.
Step S13 monitors the voice communication between the incoming call client and the contact staff, and obtains the incoming call visitor
Voice content between family and the contact staff.
In one embodiment, whether can be monitored in real time has voice logical between the incoming call client and the contact staff
Words obtain voice content when having monitored voice communication.The voice content can be incoming call client and pass through with customer service ditch
Real-time voice record in journey, can be recorded to obtain the voice by the voice content to incoming call client and contact staff
Content.
In one embodiment, when monitoring to carry out voice communication between the incoming call client and the contact staff,
Customer service voices can be extracted from the voice content, and Emotion identification is carried out to the customer service voices, to obtain the customer service
The Emotion identification of personnel exports default mood and guides content to described as a result, when the Emotion identification result is unhealthy emotion
Contact staff avoids contact staff excited, prompts customer service experience.
In one embodiment, the processing such as noise reduction, cutting, role's identification can be carried out, to the voice content with from institute
It states and extracts customer service voices in voice content.It can be according to the Emotion identification model obtained based on neural network model training to customer service
Voice carries out Emotion identification, generates Emotion identification result corresponding with the customer service voices.Specifically, the Emotion identification model
It can train and obtain in the following manner: establish neural network model, obtain the voice for training the neural network model
Content sample, and mood mark is carried out to voice content sample；Using the voice content sample after mark to deep neural network
Model is trained study, obtains the Emotion identification model for carrying out Emotion identification.The language of different people is in frequency domain
Feature can be entirely different, the different moods of the same person be embodied in the feature on frequency spectrum be also it is entirely different, be based on these
Information is labeled by the frequency spectrum manually to different people difference mood, then passes through neural network algorithm (such as cyclic convolution nerve
Network RNN) model training is carried out, the mood for identifying every a word is gone by Emotion identification model, forms a mood dialogue sequence
Column, the mood dialogue sequence can accurately assess emotional change of the customer service in dialog procedure.When dialogue sometime
When the Emotion identification result of node is unhealthy emotion, default mood guidance content is exported to contact staff, to remind customer service to need
Current emotional is carried out control or carries out mood to contact staff to pacify.
In one embodiment, it can be obtained according to the cutting to the customer service voices multiple with chronological order pass
Multiple voice segments are input in Emotion identification network model according to the chronological order and carry out feelings by the voice segment of system
Thread identification, obtains corresponding multiple Emotion identifications as a result, according to the chronological order, by multiple Emotion identification results respectively
It is integrated into the mood sequence.
Step S14 carries out text conversion to the voice content and extracts an at least keyword from the text after conversion.
In one embodiment, call can be converted for the voice content text using default speech recognition algorithm
Text.The default speech recognition algorithm refers to can algorithm by speech recognition at text.The call text refers to text
The dialog context recording text that font formula embodies.For example, can using hidden Markov model (Hidden Markov Model,
HMM) algorithm, dynamic time consolidation (Dynamic Time Warping, DTW) algorithm or be based on deep-neural-network (Deep
Neural Network, DNN) algorithm come realize to voice content carry out speech recognition.Specifically, voice content can be carried out
Noise filtering/noise reduction, sentence segmentation and sentence conversion process, to convert corresponding word element for voice content, then will
Word element after conversion is matched with the benchmark word in corresponding quality inspection term data, and the word combination after matching is risen
To obtain call text.
In one embodiment, the word element after conversion is carried out with the benchmark word in corresponding quality inspection term data
It, can be using Forward Maximum Method method, reverse maximum matching method, smallest match method or maximum matching method etc. when matching example
It is matched.
In one embodiment, TF-IDF algorithm can be used to extract keyword from the call text.TF-IDF
Algorithm can be used for assessing a words for the significance level in a subject text.The importance of words can be as it be in text
The directly proportional increase of the number of middle appearance.When carrying out TF-IDF calculating, certain is obtained by word frequency (TF) and inverse document frequency (IDF)
The TF-IDF value of a words, the TFIDF value is bigger if the importance of the words to call text the high.It therefore can be by TF-
IDF value comes keyword of the several words of foremost as the call text.For example, TF-IDF value to be come to the words of first five
Keyword as the call text.
In one embodiment, the customer service demand of TF-IDF algorithm and the prediction is also based on from the text after conversion
An at least keyword described in middle extraction.For example, if being only that TF-IDF value can be come foremost using TF-IDF algorithm
Keyword (words that TF-IDF value come first five) of several words as the call text.If based on TF-IDF algorithm and described
When the customer service demand of prediction extracts keyword from the text after conversion, can compare analysis TF-IDF value it is relatively forward and with visitor
Take the associated keyword of desired content, for example, obtained result may be TF-IDF value make number one, second, the 5th
Position, the 7th, the 9th words be the keyword that need to be extracted.It can be with when words is associated with the customer service desired content of prediction
Weight is set as a, weight can be set when words is not associated with the customer service desired content of prediction as b, TF-IDF value ranks not
It is corresponding to different weights with can equally quantify, a value is obtained by carrying out multiplying to two weights, in basis
The sequence of the value comes it is determined that choosing those words as keyword.
Step S15, the current business changing interface for the integrated service system that the contact staff logs in extremely is mentioned with described
The operation system interface of at least keyword match taken.
In one embodiment, since the integrated service system integration has original multiple systems, it is only necessary to primary to log in
It may have access to the data of original all operation systems, original multiple operation systems can be packaged into menu bar described integrated
It is shown in operation system.The mapping table of keyword Yu multiple operation systems can be pre-established, to realize that basis is extracted
Keyword by the current business changing interface of contact staff to operation system interface with the keyword match of the extraction, into
And contact staff is facilitated to carry out data query, manual switching is carried out without contact staff.
In one embodiment, when carrying out changing interface, confirmation prompting frame can also be popped up and carried out really for contact staff
Recognize, again by current business changing interface to the business with the keyword match of the extraction after confirming that prompting frame is clicked triggering
System interface.
It is understood that automatic switching function can also be closed, contact staff clicks the dish of integrated service system manually
Singly realize business changing interface.
Embodiment two:
Fig. 2 is the step flow chart of multi-service interface switching method another preferred embodiment of the present invention.According to different need
It asks, the sequence of step can change in the flow chart, and certain steps can be omitted.Compared to Figure 1, the multi-service interface is cut
The method of changing further includes step S16 and step S17.
S16, according to after voice conversion text and at least one crucial word analysis obtain the incoming call client's
Incoming call reason.
S17, the work order classification for determining the incoming call reason, by the service work order information typing of the contact staff work
Under single classification.
In one embodiment, text after contact staff completes this telephone service, after being converted to the voice
This and the keyword are analyzed to obtain the incoming call reason of this incoming call client.And according to default classifying rules to the incoming call
Reason carries out work order classification, then will be under the service work order information typing of this contact staff to work order classification.The service
Work order information may include incoming call customer information, contact staff's information, incoming call reason, client's demand, issue-resolution etc..It can
To preset a variety of incoming call reasons, and according to after voice conversion text and the keyword come be calculated belong to it is every
A kind of similarity for reason of sending a telegram here, then obtains the incoming call reason of this incoming call client according to the phase knowledge and magnanimity being calculated.Institute
Stating default classifying rules can be the mapping relations of each incoming call reason pre-established and work order classification.
Above-mentioned multi-service interface switching method, according to the phone information of access can look-ahead incoming call client customer service need
It asks, preferably can provide counseling services for incoming call client, after closing of the circuit, analyze and convert in real time using speech recognition technology
Call voice is call text, to grab the automatic switchover that keyword realizes related service system interface, while in dialog procedure
Speech, the mood of middle real-time monitoring contact staff, and properly art guidance and mood are pacified to visitor according to monitoring result push
Take personnel, can also according to after conversion call content of text and keyword to this incoming call client incoming call reason carry out intelligence
Classification, and customer service work order automatic input is carried out, improve the order efficiency of contact staff and the use body of customer service and client both sides
It tests.
Embodiment three:
Fig. 3 is the functional block diagram of multi-service changing interface device preferred embodiment of the present invention.
As shown in fig.3, the multi-service changing interface device 10 may include that data obtains module 101, prediction module
102, voice obtains module 103, extraction module 104, switching module 105, analysis module 106 and recording module 107.
When having telephone access, the data obtains the visitor that module 101 obtains incoming call client according to the phone information of access
Family data.
In one embodiment, before answering the call, contact staff can according to itself account password or face characteristic or
Vocal print feature logs in integrated service system, which is a customer service system, and can polymerize has existing multiple business
The data of system, when the customer service demand for needing to meet incoming call client carries out data query, contact staff is not necessarily to multiple
It is switched between operation system, customer service efficiency can be improved.
In one embodiment, the database data of multiple operation systems can be integrated by structure together by ETL technology
Build a total Database.Specifically, it can use ETL tool and extract data from each database to a middle layer, to extraction
Data carry out cleaning operation, undesirable data filtering is fallen, such as wrong data, deficiency of data, repeat number
According to etc., then the data progress data conversion of cleaning, for example carry out unification (title, template, standard, computation rule etc. of format
Carry out unification), the combination of data/field segmentation or calculate, finally by the data set after conversion process according to predetermined physical
The table structure of data model definitions is fitted into the tables of data of total Database.Integrated service system is developed in front end based on the total Database
System, the integrated service system integration have the function of original multiple operation systems, and contact staff can be by logging in the integrated industry
Business system carries out data query.
When having telephone access, the data, which obtains module 101, can obtain incoming call client according to the phone information of access
Customer data.The total Database stores customer profile, includes, but are not limited to, the identity data of client (such as identification card number
Code, gender, birthday, telephone number, address etc.), buy or used commodity or the data of service (such as declaration form number, declaration form
Content, financial products, financial debt-credit, settlement of insurance claim service etc.), consumer record (such as date, place, means of payment etc.), work
The information such as dynamic record (such as application Claims Resolution etc.), customer service system contact record (such as customer complaint, consulting).For example, the visitor
Family data may include insurer's essential information, declaration form number, premium content, beneficiary's information, payment situation, Claims Resolution record
Deng.
In one embodiment, the devices such as fixed-line telephone, mobile phone, smart watch access visitor can be used in incoming call client
Dress system establishes the session with contact staff.The customer data further includes incoming call client when accessing customer service system, according to
Intelligent voice system guides the customer information of input or the Demand and service information of selection.For example, incoming call client can be by phone
Virtual key (such as number 0-9, # key, * key etc.) input customer information, including but not limited to ID card No., the date of birth,
Declaration form number, product serial number, service password etc..
The prediction module 102 predicts the customer service demand of the incoming call client according to the customer data, and by prediction
Customer service demand is presented to the contact staff for docking the incoming call client.
In one embodiment, the prediction module 102 can divide the customer data according to default algorithm
Analysis, to predict that the customer service demand of incoming call client, the default algorithm can be bayesian algorithm, decision Tree algorithms etc..Than
Such as, it can use decision Tree algorithms to believe incoming call client's business datum handled recently, the business information that will expire, business arrearage
Breath etc. is analyzed the customer service demand to predict incoming call client.When the user that sends a telegram here accesses the customer service system, the connection date is
Client's premium withhold the date front and back 10 days in, can be predicted the user customer service demand may be paid with premium it is related.It can
The customer demand of prediction is shown in the currently used display equipment (such as computer screen) of contact staff.
In one embodiment, the prediction module 102 can also draw displaying customer portrait according to the customer data,
And the customer portrait drawn is shown in the display equipment.
It in one embodiment, can be with after the prediction module 102 prediction obtains the customer service demand of the incoming call client
According to the customer service demand determine it is matched if art guide document, and by the words art guide document be presented to the customer service
Personnel.Since each contact staff's communication capability is different, especially for contact staff recently, refer to if lacking standard words art
Draw, when purely dependence personal experience links up, communication effectiveness, efficiency may be undesirable, therefore can be according to the prediction
The default words art of customer service demand output guides document, and guides document to be presented to the contact staff the default words art.
It should be understood that the prediction module 102, which can pre-establish multiple words arts, guides document, not each words art refers to
Quotation shelves establish label, and then customer service demand best with prediction can be determined according to customer service demand and the matching degree of label
Art guides document if matching.
In one embodiment, when the phone of the incoming call client is switched on, art is talked about for the versatility of early period, it can be with
Broadcasted by presetting the sound of contact staff that incoming call client is currently docked in speech synthesis system synthesis, contact staff without
It all repeats to say when need to receive calls every time primary.
The voice obtains module 103 and monitors the voice communication sent a telegram here between client and the contact staff, and obtains
Take the voice content between the incoming call client and the contact staff.
In one embodiment, the voice, which obtains module 103, can be monitored in real time the incoming call client and the customer service
Whether there is voice communication between personnel, when having monitored voice communication, obtains voice content.The voice content, which can be, to be come
Electric client records with the real-time voice in customer service communication process, can pass through the voice content to incoming call client and contact staff
It is recorded to obtain the voice content.
In one embodiment, when monitoring to carry out voice communication between the incoming call client and the contact staff,
The voice obtains module 103 can extract customer service voices from the voice content, and carry out mood to the customer service voices
Identification, to obtain the Emotion identification of the contact staff as a result, when the Emotion identification result is unhealthy emotion, output is default
Mood guides content to the contact staff, avoids contact staff excited, prompts customer service experience.
In one embodiment, the voice, which obtains module 103, can carry out noise reduction, cutting, angle to the voice content
The processing such as color identification, to extract customer service voices from the voice content.It can be obtained according to based on neural network model training
Emotion identification model Emotion identification is carried out to customer service voices, generate corresponding with customer service voices Emotion identification result.Tool
Body, the Emotion identification model can be trained in the following manner and be obtained: being established neural network model, obtained for training
The voice content sample of neural network model is stated, and mood mark is carried out to voice content sample；Using in the voice after mark
Hold sample and study is trained to deep neural network model, obtains the Emotion identification model for carrying out Emotion identification.It is different
Feature of the language in frequency domain of people can be entirely different, the different moods of the same person, which are embodied in the feature on frequency spectrum, is also
Entirely different, these information are based on, are labeled by the frequency spectrum manually to different people difference mood, then pass through neural network
Algorithm (such as cyclic convolution neural network RNN) carries out model training, and the mood for identifying every a word is gone by Emotion identification model,
A mood dialogue sequence is formed, the mood dialogue sequence can accurately assess mood of the customer service in dialog procedure and become
Change.When the Emotion identification result of the sometime node of dialogue is unhealthy emotion, exports default mood and guide content to customer service
Personnel, to remind customer service to need to carry out current emotional control or carry out mood to contact staff to pacify.
In one embodiment, the voice acquisition module 103 can obtain more according to the cutting to the customer service voices
Multiple voice segments are input to mood according to the chronological order by a voice segment with chronological order relationship
Emotion identification is carried out in identification network model, obtains corresponding multiple Emotion identifications respectively as a result, suitable according to the time order and function
Multiple Emotion identification results are integrated into the mood sequence by sequence.
The extraction module 104 carries out text conversion to the voice content and extracts at least one from the text after conversion
Keyword.
In one embodiment, the extraction module 104 can use default speech recognition algorithm will be in the voice
Hold text and is converted into call text.The default speech recognition algorithm refers to can algorithm by speech recognition at text.It is described
Call text refers to the dialog context recording text embodied with written form.For example, hidden Markov model can be used
(Hidden Markov Model, HMM) algorithm, dynamic time consolidation (Dynamic Time Warping, DTW) algorithm or
It is realized based on deep-neural-network (Deep Neural Network, DNN) algorithm and speech recognition is carried out to voice content.Tool
Body, voice content can be carried out to noise filtering/noise reduction, sentence segmentation and sentence conversion process, so that voice content be turned
It turns to corresponding word element, then word element and the benchmark word in corresponding quality inspection term data after conversion is carried out
Match, the word combination after matching is got up to obtain call text.
In one embodiment, the extraction module 104 is by word element and the corresponding quality inspection term data after conversion
In benchmark word when carrying out matching example, such as Forward Maximum Method method, reverse maximum matching method, smallest match method can be used
Or maximum matching method etc. is matched.
In one embodiment, TF-IDF algorithm can be used to mention from the call text in the extraction module 104
Take keyword.TF-IDF algorithm can be used for assessing a words for the significance level in a subject text.Words it is important
The directly proportional increase of number that property can occur in the text with it.When carrying out TF-IDF calculating, pass through word frequency (TF) and inverse text
Shelves frequency (IDF) obtains the TF-IDF value of some words, if the words the high to the importance of call text the TFIDF value more
Greatly.Therefore TF-IDF value can be come to several words of foremost as the keyword of the call text.For example, by TF-IDF
Value comes keyword of the words of first five as the call text.
In one embodiment, the extraction module 104 is also based on TF-IDF algorithm and the customer service of the prediction and needs
It asks and extracts an at least keyword from the text after conversion.For example, can be by TF- using TF-IDF algorithm if being only
IDF value comes keyword (words that TF-IDF value come first five) of several words as the call text of foremost.If base
When TF-IDF algorithm and the customer service demand of the prediction extract keyword from the text after conversion, analysis TF- can be compared
IDF value is relatively forward and associated with customer service desired content keyword, for example obtained result may be that TF-IDF value comes
First, second, the 5th, the 7th, the 9th words be the keyword that need to be extracted.When the customer service of words and prediction needs
Weight can be set as a when asking content associated, can set weight when words is not associated with the customer service desired content of prediction
For b, TF-IDF value ranking difference can equally quantify to correspond to different weights, by carrying out multiplyings to two weights
A value is obtained, in the sequence according to the value come it is determined that choosing those words as keyword.
The current business changing interface for the integrated service system that the switching module 105 is used to log in the contact staff
To the operation system interface with an at least keyword match for the extraction.
In one embodiment, since the integrated service system integration has original multiple systems, it is only necessary to primary to log in
It may have access to the data of original all operation systems, original multiple operation systems can be packaged into menu bar described integrated
It is shown in operation system.The switching module 105 can pre-establish the mapping table of keyword Yu multiple operation systems, come
Realize according to the keyword that extracts by the current business changing interface of contact staff to the keyword match of the extraction
Operation system interface, and then contact staff is facilitated to carry out data query, manual switching is carried out without contact staff.
In one embodiment, the switching module 105 can also pop up confirmation prompting frame and supply when carrying out changing interface
Contact staff confirms, again by current business changing interface to the pass with the extraction after confirming that prompting frame is clicked triggering
The matched operation system interface of key word.
It is understood that automatic switching function can also be closed, contact staff clicks the dish of integrated service system manually
Singly realize business changing interface.
The analysis module 106 be used for according to after voice conversion text and at least one crucial word analysis obtain
The incoming call reason of the incoming call client.
The recording module 107 is used to determine the work order classification of the incoming call reason, by the service of the contact staff
Under the classification of the work order information typing work order.
In one embodiment, after contact staff completes this telephone service, the analysis module 106 can be to described
Text and the keyword after voice conversion are analyzed to obtain the incoming call reason of this incoming call client.It can preset more
Kind of incoming call reason, the analysis module 106 can be converted according to the voice after text and the keyword be calculated
The similarity for belonging to each incoming call reason, the incoming call that this incoming call client is then obtained according to the phase knowledge and magnanimity being calculated are former
Cause.
The recording module 107 can carry out work order classification to the incoming call reason according to default classifying rules, then incite somebody to action this
Under the service work order information typing of secondary contact staff is classified to the work order.The service work order information may include incoming call client's letter
Breath, contact staff's information, incoming call reason, client's demand, issue-resolution etc..The default classifying rules can be to be built in advance
The mapping relations of vertical each incoming call reason and work order classification.
Above-mentioned multi-service changing interface device, according to the phone information of access can look-ahead incoming call client customer service need
It asks, preferably can provide counseling services for incoming call client, after closing of the circuit, analyze and convert in real time using speech recognition technology
Call voice is call text, to grab the automatic switchover that keyword realizes related service system interface, while in dialog procedure
Speech, the mood of middle real-time monitoring contact staff, and properly art guidance and mood are pacified to visitor according to monitoring result push
Take personnel, can also according to after conversion call content of text and keyword to this incoming call client incoming call reason carry out intelligence
Classification, and customer service work order automatic input is carried out, improve the order efficiency of contact staff and the use body of customer service and client both sides
It tests.
Fig. 4 is the schematic diagram of computer installation preferred embodiment of the present invention.
The computer installation 1 includes memory 20, processor 30 and is stored in the memory 20 and can be in institute
State the computer program 40 run on processor 30, such as multi-service changing interface program.The processor 30 executes the meter
Realize the step in above-mentioned multi-service interface switching method embodiment when calculation machine program 40, such as step S11 shown in FIG. 1~
S15 or step S11~S17 shown in Fig. 2.Alternatively, the processor 30 realized when executing the computer program 40 it is above-mentioned more
The function of each module in business changing interface Installation practice, such as the module 101~107 in Fig. 3.
Illustratively, the computer program 40 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 20, and are executed by the processor 30, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, and described instruction section is used
In implementation procedure of the description computer program 40 in the computer installation 1.For example, the computer program 40 can be with
It is divided into the data in Fig. 3 and obtains module 101, prediction module 102, voice acquisition module 103, extraction module 104, switching mould
Block 105, analysis module 106 and recording module 107.Each module concrete function is referring to embodiment three.
The computer installation 1 can be desktop PC, notebook, palm PC, mobile phone, tablet computer and cloud
Server etc. calculates equipment.It will be understood by those skilled in the art that the schematic diagram is only the example of computer installation 1, and
The restriction to computer installation 1 is not constituted, may include components more more or fewer than diagram, or combine certain components, or
The different component of person, such as the computer installation 1 can also include input-output equipment, network access equipment, bus etc..
Alleged processor 30 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor 30 is also possible to any conventional processing
Device etc., the processor 30 are the control centres of the computer installation 1, utilize various interfaces and the entire computer of connection
The various pieces of device 1.
The memory 20 can be used for storing the computer program 40 and/or module/unit, and the processor 30 passes through
Operation executes the computer program and/or module/unit being stored in the memory 20, and calls and be stored in memory
Data in 20 realize the various functions of the computer installation 1.The memory 20 can mainly include storing program area and deposit
Store up data field, wherein storing program area can application program needed for storage program area, at least one function (for example sound is broadcast
Playing function, image player function etc.) etc.；Storage data area, which can be stored, uses created data (ratio according to computer installation 1
Such as audio data, phone directory) etc..In addition, memory 20 may include high-speed random access memory, it can also include non-easy
The property lost memory, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other
Volatile solid-state part.
If the integrated module/unit of the computer installation 1 is realized in the form of SFU software functional unit and as independence
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, of the invention
It realizes all or part of the process in above-described embodiment method, can also instruct relevant hardware come complete by computer program
At the computer program can be stored in a computer readable storage medium, and the computer program is held by processor
When row, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code, institute
Stating computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..It is described
Computer-readable medium may include: any entity or device, recording medium, U that can carry the computer program code
Disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs
It is bright, the content that the computer-readable medium includes can according in jurisdiction make laws and patent practice requirement into
Row increase and decrease appropriate, such as do not include electric load according to legislation and patent practice, computer-readable medium in certain jurisdictions
Wave signal and telecommunication signal.
In several embodiments provided by the present invention, it should be understood that disclosed computer installation and method, it can be with
It realizes by another way.For example, computer installation embodiment described above is only schematical, for example, described
The division of unit, only a kind of logical function partition, there may be another division manner in actual implementation.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in same treatment unit
It is that each unit physically exists alone, can also be integrated in same unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.It is stated in computer installation claim
Multiple units or computer installation can also be implemented through software or hardware by the same unit or computer installation.The
One, the second equal words are used to indicate names, and are not indicated any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. a kind of multi-service interface switching method, which is characterized in that the described method includes:
When having telephone access, the customer data of incoming call client is obtained according to the phone information of access；
The customer service demand of the incoming call client is predicted according to the customer data, and the customer service demand of prediction is presented to docking institute
State the contact staff of incoming call client；
The voice communication between the incoming call client and the contact staff is monitored, and obtains the incoming call client and the customer service
Voice content between personnel；
Text conversion is carried out to the voice content and extracts an at least keyword from the text after conversion；And
The current business changing interface for the integrated service system that the contact staff is logged in is closed to at least the one of the extraction
The matched operation system interface of key word.
2. multi-service interface switching method as described in claim 1, which is characterized in that the integrated service system integration has more
Before the step of a operation system, the customer data that incoming call client is obtained according to the phone information of access further include:
Data pick-up operation is carried out to the database of each operation system, and carries out cleaning behaviour for obtained data are extracted
Make, to filter the data for not meeting preset requirement；
Data after cleaning are subjected to data conversion, and the data after conversion process are defined according to preset data model
Table structure is fitted into the tables of data of a total Database；And
It develops to obtain the integrated service system based on the total Database.
3. multi-service interface switching method as claimed in claim 1 or 2, which is characterized in that described according to the customer data
After the step of predicting the customer service demand of the incoming call client further include:
It determines if match with the customer service demand of the prediction that art guides document, and the words art is guided described in document is presented to
Contact staff.
4. multi-service interface switching method as claimed in claim 1 or 2, which is characterized in that it is described to the voice content into
It composes a piece of writing this conversion and the step of extracting an at least keyword from the text after conversion includes:
Text conversion is carried out to the voice content, and the customer service demand based on TF-IDF algorithm and the prediction is after conversion
An at least keyword is extracted in text.
5. multi-service interface switching method as claimed in claim 1 or 2, which is characterized in that described to obtain the incoming call client
After the step of voice content between the contact staff further include:
Customer service voices are extracted from the voice content, and Emotion identification is carried out to the customer service voices, to obtain the customer service
The Emotion identification result of personnel；And
When the Emotion identification result is unhealthy emotion, exports default mood and guide content to the contact staff.
6. multi-service interface switching method as claimed in claim 5, which is characterized in that described to be extracted from the voice content
Customer service voices, and Emotion identification is carried out to the customer service voices, the step of to obtain the Emotion identification result of the contact staff
Include:
It is established according to multiple voice sample datas and trains to obtain an Emotion identification model；
The mostly described voice content carries out noise reduction, cutting and role and identifies operation, to extract the customer service voices；And
The customer service voices are input to the Emotion identification model, to obtain the Emotion identification result of the contact staff.
7. multi-service interface switching method as claimed in claim 1 or 2, which is characterized in that the method also includes:
Text and at least one crucial word analysis after being converted according to the voice obtain the incoming call reason of the incoming call client；
And
The work order classification for determining the incoming call reason, service work order information typing work order of the contact staff is classified
Under；
Wherein, the service work order information includes at least incoming call customer information, contact staff's information, incoming call reason.
8. a kind of multi-service changing interface device, which is characterized in that described device includes:
Data obtains module, for obtaining the customer data of incoming call client according to the phone information of access when having telephone access；
Prediction module for predicting the customer service demand of the incoming call client according to the customer data, and the customer service of prediction is needed
Ask the contact staff for being presented to and docking the incoming call client；
Voice obtains module, for monitoring the voice communication between the incoming call client and the contact staff, and described in acquisition
The voice content sent a telegram here between client and the contact staff；
Extraction module, for carrying out text conversion to the voice content and extracting at least one key from the text after conversion
Word；And
The current business changing interface of switching module, the integrated service system for logging in the contact staff is extremely mentioned with described
The operation system interface of at least keyword match taken.
9. a kind of computer installation, the computer installation includes processor and memory, is stored on the memory several
Computer program, which is characterized in that such as right is realized when the processor is for executing the computer program stored in memory
It is required that described in any one of 1-7 the step of multi-service interface switching method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of multi-service interface switching method as described in any one of claim 1-7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910578491.0A CN110475032A (en) | 2019-06-28 | 2019-06-28 | Multi-service interface switching method, device, computer installation and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910578491.0A CN110475032A (en) | 2019-06-28 | 2019-06-28 | Multi-service interface switching method, device, computer installation and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110475032A true CN110475032A (en) | 2019-11-19 |
Family
ID=68507086
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910578491.0A Pending CN110475032A (en) | 2019-06-28 | 2019-06-28 | Multi-service interface switching method, device, computer installation and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110475032A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583968A (en) * | 2020-05-25 | 2020-08-25 | 桂林电子科技大学 | Speech emotion recognition method and system |
| CN111988477A (en) * | 2020-09-02 | 2020-11-24 | 中国银行股份有限公司 | Incoming call processing method and device, server and storage medium |
| CN112348667A (en) * | 2020-10-30 | 2021-02-09 | 广州佰锐网络科技有限公司 | Intelligent account opening method and device based on virtual customer service |
| CN112508295A (en) * | 2020-12-16 | 2021-03-16 | 国家电网有限公司客户服务中心 | Incoming call service prediction method and system based on service map and Markov model |
| CN112565533A (en) * | 2021-02-22 | 2021-03-26 | 深圳市优讯通信息技术有限公司 | Telephone switching method, electronic equipment and computer storage medium |
| CN113507541A (en) * | 2021-07-02 | 2021-10-15 | 马上消费金融股份有限公司 | Incoming call intention display method and device |
| CN113837545A (en) * | 2021-08-25 | 2021-12-24 | 广西电网有限责任公司 | Electric power customer service system with real-time monitoring service quality |
| CN114025044A (en) * | 2021-10-15 | 2022-02-08 | 中国人民财产保险股份有限公司 | Control method and device of call center and electronic equipment |
| CN116523218A (en) * | 2023-04-11 | 2023-08-01 | 深圳微应科技有限公司 | Service personnel matching method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM534864U (en) * | 2016-06-29 | 2017-01-01 | 國泰人壽保險股份有限公司 | Customer service system |
| TW201801021A (en) * | 2016-06-29 | 2018-01-01 | 國泰人壽保險股份有限公司 | Customer service system |
| US20180090142A1 (en) * | 2016-09-27 | 2018-03-29 | Fmr Llc | Automated software execution using intelligent speech recognition |
| CN108062316A (en) * | 2016-11-08 | 2018-05-22 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for aiding in customer service |
| CN109033257A (en) * | 2018-07-06 | 2018-12-18 | 中国平安人寿保险股份有限公司 | Talk about art recommended method, device, computer equipment and storage medium |
| CN109618068A (en) * | 2018-11-08 | 2019-04-12 | 上海航动科技有限公司 | A kind of voice service method for pushing, device and system based on artificial intelligence |
| CN109767791A (en) * | 2019-03-21 | 2019-05-17 | 中国—东盟信息港股份有限公司 | A kind of voice mood identification and application system conversed for call center |
-
2019
- 2019-06-28 CN CN201910578491.0A patent/CN110475032A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWM534864U (en) * | 2016-06-29 | 2017-01-01 | 國泰人壽保險股份有限公司 | Customer service system |
| TW201801021A (en) * | 2016-06-29 | 2018-01-01 | 國泰人壽保險股份有限公司 | Customer service system |
| US20180090142A1 (en) * | 2016-09-27 | 2018-03-29 | Fmr Llc | Automated software execution using intelligent speech recognition |
| CN108062316A (en) * | 2016-11-08 | 2018-05-22 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for aiding in customer service |
| CN109033257A (en) * | 2018-07-06 | 2018-12-18 | 中国平安人寿保险股份有限公司 | Talk about art recommended method, device, computer equipment and storage medium |
| CN109618068A (en) * | 2018-11-08 | 2019-04-12 | 上海航动科技有限公司 | A kind of voice service method for pushing, device and system based on artificial intelligence |
| CN109767791A (en) * | 2019-03-21 | 2019-05-17 | 中国—东盟信息港股份有限公司 | A kind of voice mood identification and application system conversed for call center |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583968A (en) * | 2020-05-25 | 2020-08-25 | 桂林电子科技大学 | Speech emotion recognition method and system |
| CN111988477A (en) * | 2020-09-02 | 2020-11-24 | 中国银行股份有限公司 | Incoming call processing method and device, server and storage medium |
| CN112348667A (en) * | 2020-10-30 | 2021-02-09 | 广州佰锐网络科技有限公司 | Intelligent account opening method and device based on virtual customer service |
| CN112508295A (en) * | 2020-12-16 | 2021-03-16 | 国家电网有限公司客户服务中心 | Incoming call service prediction method and system based on service map and Markov model |
| CN112565533A (en) * | 2021-02-22 | 2021-03-26 | 深圳市优讯通信息技术有限公司 | Telephone switching method, electronic equipment and computer storage medium |
| CN112565533B (en) * | 2021-02-22 | 2021-05-04 | 深圳市优讯通信息技术有限公司 | Telephone switching method, electronic equipment and computer storage medium |
| CN113507541A (en) * | 2021-07-02 | 2021-10-15 | 马上消费金融股份有限公司 | Incoming call intention display method and device |
| CN113837545A (en) * | 2021-08-25 | 2021-12-24 | 广西电网有限责任公司 | Electric power customer service system with real-time monitoring service quality |
| CN114025044A (en) * | 2021-10-15 | 2022-02-08 | 中国人民财产保险股份有限公司 | Control method and device of call center and electronic equipment |
| CN116523218A (en) * | 2023-04-11 | 2023-08-01 | 深圳微应科技有限公司 | Service personnel matching method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11004013B2 (en) | Training of chatbots from corpus of human-to-human chats | |
| CN110475032A (en) | Multi-service interface switching method, device, computer installation and storage medium | |
| US11847422B2 (en) | System and method for estimation of interlocutor intents and goals in turn-based electronic conversational flow | |
| US20200175964A1 (en) | System and Method for a Computer User Interface for Exploring Conversational Flow with Selectable Details | |
| US10824814B2 (en) | Generalized phrases in automatic speech recognition systems | |
| CN105874530B (en) | Predicting phrase recognition quality in an automatic speech recognition system | |
| US11107006B2 (en) | Visualization, exploration and shaping conversation data for artificial intelligence-based automated interlocutor training | |
| KR102100214B1 (en) | Method and appratus for analysing sales conversation based on voice recognition | |
| EP4036823A1 (en) | Customization platform and method for service quality evaluation product | |
| EP3446267A1 (en) | Quality monitoring automation in contact centers | |
| JP6865653B2 (en) | Dialogue analysis system and dialogue analysis program | |
| US11798539B2 (en) | Systems and methods relating to bot authoring by mining intents from conversation data via intent seeding | |
| US8781880B2 (en) | System, method and apparatus for voice analytics of recorded audio | |
| CN110633912A (en) | Method and system for monitoring service quality of service personnel | |
| US20200092419A1 (en) | Systems And Methods For Sensing Emotion In Voice Signals And Dynamically Changing Suggestions In A Call Center | |
| US10620799B2 (en) | Processing system for multivariate segmentation of electronic message content | |
| US20230237276A1 (en) | System and Method for Incremental Estimation of Interlocutor Intents and Goals in Turn-Based Electronic Conversational Flow | |
| Shah et al. | A review of natural language processing in contact centre automation | |
| KR20210009266A (en) | Method and appratus for analysing sales conversation based on voice recognition | |
| CN111949777A (en) | Intelligent voice conversation method and device based on crowd classification and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191119 |