CN109040482A - The unattended intelligent phone inquiry method, system and device of field of securities - Google Patents
The unattended intelligent phone inquiry method, system and device of field of securities Download PDFInfo
- Publication number
- CN109040482A CN109040482A CN201810903110.7A CN201810903110A CN109040482A CN 109040482 A CN109040482 A CN 109040482A CN 201810903110 A CN201810903110 A CN 201810903110A CN 109040482 A CN109040482 A CN 109040482A
- Authority
- CN
- China
- Prior art keywords
- voice
- mrcpserver
- system module
- cti system
- channel
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000011664 signaling Effects 0.000 claims description 18
- 230000015572 biosynthetic process Effects 0.000 claims description 17
- 238000012544 monitoring process Methods 0.000 claims description 17
- 238000003786 synthesis reaction Methods 0.000 claims description 17
- 238000004321 preservation Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 2
- 238000000151 deposition Methods 0.000 claims 2
- 230000005389 magnetism Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 10
- 239000000284 extract Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000977 initiatory effect Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000033748 Device issues Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- H04M3/527—Centralised call answering arrangements not requiring operator intervention
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; 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 TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- 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
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Signal Processing (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of unattended intelligent phone inquiry method, system and device of field of securities, technology contents are main are as follows: when user puts through phone, into CTI system automatic-answering back device inlet wire, and play welcoming address voice；The problem of user says oneself according to IVR voice prompting, such as stock is looked into, look into expire-services time etc.；CTI obtains keyword and executes corresponding voice routing by speech recognition user word；Such as stock is looked into, after user said stock name, CTI recognizes stock name, calls query interface, after finding current share prices, text is synthesized voice, playback is listened to user.The present invention can be provided for user can more intelligent quick inquiry service, for enterprise for telemarketing with customer service team is to the intelligent management of client and the service of higher efficiency plays an important role and application value.
Description
Technical field
The present invention relates to the present invention relates to comprising the multi-media communication technology including voice and text, it is related in communication field
ASR (Automatic Speech Recognition, speech recognition) and TTS(Text to Speech, speech synthesis) close
Key technology more particularly to a kind of telephony intelligence answering method and system, device in field of securities.
Background technique
In the network also underdeveloped age, people can only carry out business consultation by service calls.For client, electricity
Words need to listen to interminable voice prompting after connecting and multipass key selectes the service of oneself needs, such as silver in the process
End etc. must be pressed the # key after inputting ID card No. or bank's card number in row service calls, operating method is complicated.In addition, electric
The option of voice prompting can not be clearly understood for some users in words customer service, and user is possible can not be according to its language
The option of sound prompt judges the service needed for oneself.Such as user has selected the classification of a certain service, according to voice prompting into
Row finds it not after repeatedly choosing be oneself desired service, then again according to voice prompting be back to previous menu or
It returns repeatedly to firmly menu, it is cumbersome, take a long time.In view of above-mentioned usage experience, over time, user is just habitually
Manual service is directly selected after closing of the circuit, is promoted so as to cause the ratio of answering of artificial customer service, is led to intelligent voice system
Effect have a greatly reduced quality, the appearance of intelligent voice system do not contain actively its customer service system to the wilderness demand of contact staff,
Cost of labor for contact staff is still huge.
With popularizing for network, client is gradually transferred to network customer service from phone customer service, and client and contact staff directly exist
Written communication is carried out on network.Early period, there is still a need for a large amount of contact staff to carry out manual service, and the demand to contact staff is still
It is huge.Later period, intelligent customer service robot came into being with the development of artificial intelligence, intelligent customer service robot energy active analysis
The problem of client proposes, and extract corresponding answer in database and replied.However, this intelligent customer service robot is to user
Network dependency degree it is excessively high, once the network lost contact of user just can not get service.
In general, demand of the current customer service technology to user network and artificial customer service extremely relies on.With portfolio
Growth, the operation cost of customer service will necessarily continue to increase, and increase the cost pressure of operator.
Summary of the invention
To solve the problems, such as above-mentioned background technique, present invention combination ASR (Automatic Speech
Recognition, speech recognition) and TTS(Text to Speech, speech synthesis) technology, it has invented a kind of for security neck
The unattended intelligent phone inquiry method, system and device in domain.User automatically accesses the system, user after dialing service calls
The problem of the problem of according to consulting required for the autonomous statement of prompt, system receives automatically and analyzes user's statement, extract keyword
And the corresponding interface is called, its answer asked questions is provided for client, carries out voice broadcast.Its specific technical solution is as follows:
In a first aspect, the unattended intelligent phone inquiry method of field of securities, method and step are as follows:
Step 1, when user puts through phone, CTI(Computer Telephony Integration, computer telephone is integrated) module
Automatic-answering back device inlet wire.
Step 2, the voice input of the CTI system module monitoring users.
Step 3, the CTI system module obtains the voice input of user, and the CTI system module sends the voice
To MRCPServer server, the MRCPServer server carries out voice, semantics recognition to the voice, obtains institute's predicate
The crucial character/word of sound feeds back to CTI system module.
Step 4, the CTI system module executes corresponding voice road according to the classification of the crucial character/word of acquisition
By, and query interface is called to execute inquiry.
Step 5, the CTI system module gets the correlation text of corresponding key character/word in database by query interface
Relevant textual information is sent to MRCPServer server, the TTS of MRCPServer server by this information, CTI system module
The relevant textual information is converted to reply voice by plug-in unit, and plays to user.
Step 6, after reply voice finishes, the MRCPServer server plays voice prompting and asks the user whether
It needs to continue to service, and continues whether monitoring users input voice.
Step 7, step 2-6 is repeated, until the CTI system module is more than that voice has not been obtained in default listening period
It inputs, then CTI system module automatic hand-up.
With reference to first aspect, in the first possible implementation of the first aspect, the step 1 includes: to work as user
Put through phone, CTI system module automatic-answering back device inlet wire；The Condition node that CTI system module is routed by inlet wire phone is built
User is stood to the Channel A of CTI system module, carries out call connection；And by Session variable and SIP(Session
Initiation Protocol- Session initiation Protocol) information preservation is into Channel A.
The possible implementation of with reference to first aspect the first, in second of possible implementation of first aspect
In, the step 2 includes: to complete the signaling process of SIP intercommunication when CTI system module automatic-answering back device inlet wire, default when receiving
SIP status code when, it is Ready that CTI system module, which modifies the Status value in Session variable, and CTI system module continues to hold
The voice input of the preset voice routing monitoring users of row；
The possible implementation of second with reference to first aspect, in a third possible implementation of the first aspect, institute
State the value that step 3 includes: Type and Data that CTI system module is loaded by Action node in the Session variable
(Type is for determining whether CTI system module executes Data instruction), obtains the VoP of user's input；CTI system mould
Block is by VoP and SIP information guiding Mod_unimrcp module.
After the Mod_unimrcp module receives the SIP information of the Channel A, Mod_unimrcp module passes through
MRCPClient client is initiated to invite to MRCPServer server, completes the signaling process of SIP intercommunication, establishes CTI system
Module to MRCPServer server Channel B, when CTI system module receives preset SIP status code, Mod_
Unimrcp module connects Channel A with Channel B, sends the voice packet of user to by RTSP
MRCPServer server.
After MRCPServer server receives VoP, calls ASR plug-in unit to read the VoP and carry out
Voice, semantics recognition obtain the crucial character/word of the VoP, according to the weight ratio of the crucial character/word of setting, will close
Key character/word is encoded to UTF8(8-bit Unicode Transformation Format- Unicode) return to MRCPClient
In the detect_speech_result variable of client.
The third possible implementation with reference to first aspect, in the 4th kind of possible implementation of first aspect
In, the step 3 further include: the CTI system module by Action node load Type in the Session variable and
The value of Data, and execute the VoP for calling sub-process record session to obtain all user's inputs of Channel A
Save as the audio file on local disk.
Third or the 4th kind of possible implementation with reference to first aspect, in the 5th kind of possible realization of first aspect
In mode, the step 4 includes: the shell script of the CTI system module according to detect_speech_result variable
Value executes corresponding voice routing, and query interface query execution is called to inquire.
The 5th kind of possible implementation with reference to first aspect, in the 6th kind of possible implementation of first aspect
In, the step 5 includes: the text parameter hair that the query interface calls the relevant information of corresponding crucial character/word in database
It is sent to MRCPServer server；After the MRCPServer server receives the text parameter, TTS plug-in unit is called to identify institute
It states text parameter and synthesizes reply voice, the MRCPServer server is sent out the reply voice of synthesis by Channel B
It send to CTI system module, the reply voice is then played into user via Channel A.
The 6th kind of possible implementation with reference to first aspect, in the 7th kind of possible implementation of first aspect
In, the step 6 includes: after reply voice finishes, and the MRCPClient client destroys detect_speech_
UTF8 in result variable, the MRCPServer server send voice prompting and inquire whether the user needs to continue to service,
And CTI system module continues whether monitoring users input voice.
Second aspect, the unattended intelligent phone interrogation system of field of securities, system include the following:
CTI system module is used for automatic-answering back device inlet wire, carries out call connection by inlet wire phone Route establishment Channel A；And
By Session variable and SIP information preservation into Channel A；The Status value of Session variable is modified, is executed default
Voice in listening period, which inputs, to be monitored；It obtains the VoP of Channel A and calls sub-process record session
Saving the VoP is the audio file on local disk；By VoP and SIP information guiding Mod_unimrcp
Module simultaneously establishes the Channel B with MRCPServer server by MRCPClient client；Obtain MRCPServer clothes
Device be engaged in the crucial character/word of VoP progress voice, semantic analysis generation, is stored in MRCPClient client
In detect_speech_result variable, and the corresponding voice routing of the crucial character/word is executed, query interface is called to execute
Corresponding inquiry content, the text parameter for obtaining the relevant information of corresponding crucial character/word in database are sent to MRCPServer
Server；The reply voice returned by MRCPServer server is played into user by Channel A；Finish reply
Voice continues monitoring users and whether inputs voice until being more than default listening period, then automatic hand-up.
The wherein MRCPClient client, for executing the request of CTI system module to MRCPServer server
Issue invite, complete SIP intercommunication signaling process, establish CTI system module to MRCPServer server Channel B；
For UTF8 to be loaded onto detect_speech_result variable；After reply voice finishes, detect_ is destroyed
UTF8 in speech_result variable.
The Mod_unimrcp module, after the signaling process according to the completion SIP intercommunication of SIP information, described in foundation
Channel B of the CTI system module to the MRCPServer server；Preset SIP status code is received in CTI system module
When, Channel A is connected with Channel B, MRCPServer server is sent by RTSP by the voice packet of user.
MRCPServer server calls ASR plug-in unit to read the VoP for obtaining the VoP
And voice, semantics recognition are carried out, the crucial character/word of the VoP is obtained, according to the weight of the crucial character/word of setting
Than being that UTF8 is returned in the detect_speech_result variable of MRCPClient client by keyword/Chinese word coding；Institute
The text parameter that MRCPServer server obtains CTI system module polls is stated, TTS plug-in unit is called to identify the text parameter simultaneously
Reply voice is synthesized, the reply voice of synthesis is sent to by CTI system module by Channel B, via Channel A by institute
It states reply voice and plays to user, reply voice finishes, and sends voice prompting and inquires whether the user needs to continue to service.
Database, for providing query interface for the CTI system module according to detect_speech_result variable
In UTF8 inquire and obtain the text parameter of relevant information.
The third aspect, the unattended intelligent phone interrogation system device of field of securities, system and device include the following:
CTI system device is used for automatic-answering back device inlet wire, carries out call connection by inlet wire phone Route establishment Channel A；And
By Session variable and SIP information preservation into Channel A；The Status value of Session variable is modified, is executed default
Voice in listening period, which inputs, to be monitored；It obtains the VoP of Channel A and calls sub-process record session
Saving the VoP is the audio file on local disk；By VoP and SIP information guiding Mod_unimrcp
Device simultaneously establishes the Channel B with MRCPServer server unit by MRCPClient client terminal device；It obtains
The crucial character/word that MRCPServer server unit carries out voice to VoP, semantic analysis generates, is stored in
In the detect_speech_result variable of MRCPClient client terminal device, and execute the corresponding language of the crucial character/word
Sound routing, calls query interface to execute corresponding inquiry content, obtains the text of the relevant information of corresponding crucial character/word in database
This parameter is sent to MRCPServer server unit；The reply voice returned by MRCPServer server unit is passed through
Channel A plays to user；Reply voice is finished, continues whether monitoring users input voice until being more than default monitor
Time, then automatic hand-up.
The wherein MRCPClient client terminal device, the request for executing CTI system device take to MRCPServer
Business device device, which issues, invites, and completes the signaling process of SIP intercommunication, establishes CTI system device to MRCPServer server unit
Channel B；For UTF8 to be loaded onto detect_speech_result variable；After reply voice finishes, pin
Ruin the UTF8 in detect_speech_result variable.
The Mod_unimrcp device, after the signaling process according to the completion SIP intercommunication of SIP information, described in foundation
Channel B of the CTI system device to the MRCPServer server unit；Preset SIP shape is received in CTI system device
When state code, Channel A is connected with Channel B, MRCPServer clothes are sent by RTSP by the voice packet of user
Business device device.
MRCPServer server unit calls ASR plug-in unit to read the voice number for obtaining the VoP
According to wrapping and carrying out voice, semantics recognition, the crucial character/word of the VoP is obtained, according to the power of the crucial character/word of setting
Compare again, the detect_speech_result that keyword/Chinese word coding is UTF8 back to MRCPClient client terminal device is become
In amount；The MRCPServer server unit obtains the text parameter of CTI system device inquiry, and TTS plug-in unit is called to identify institute
It states text parameter and synthesizes reply voice, the reply voice of synthesis is sent to by CTI system module by Channel B, via
The reply voice is played to user by Channel A, and reply voice finishes, and is sent voice prompting and is asked the user whether to need
Continue to service.
Data library device, for providing query interface for the CTI system device according to detect_speech_result
UTF8 in variable is inquired and is obtained the text parameter of relevant information.
It further include computer readable storage means, central processing unit, bus；The computer readable storage means are in
Central processor and CTI system device, MRCPClient client terminal device, Mod_unimrcp device, MRCPServer server dress
It sets, data library device is attached by bus；The computer readable storage means are stored with a plurality of operational order for center
Processor calls, and the central processing unit executes first to the 7th kind that the operational order realizes first aspect and first aspect
Method described in possible implementation.
The utility model has the advantages that
1. realizing that phone inquiry is unattended substantially, it is only necessary to be equipped with a small amount of contact staff and handle a small amount of manual service, significantly
Reduce customer service cost of labor.
2. realizing the service of user self-help express query, user is not required to clothes required for passively selecting according to voice prompting
Business, and proposition its demand for services that can be autonomous, greatly improve the service rate and service quality of service system, bring to user
More smooth, comfortable service experience.
3. realize the diversified intelligent Service of telephone system, even if in the case where user services without network, it still can be with
Intelligent query service is obtained, accessible inquiry is realized, better service guarantee is provided.
In view of this, the present invention can be provided for user can more intelligent quick inquiry service, be enterprise for phone battalion
It sells and customer service team is to the intelligent management of client and the service of higher efficiency plays an important role and application value.
Detailed description of the invention
Fig. 1 is the flow diagram of the embodiment of the present invention one；
Fig. 2 is the schematic diagram data in the Session variable of the embodiment of the present invention one；
Fig. 3 is the timing diagram of the embodiment of the present invention one；
Fig. 4 is the system framework figure of the embodiment of the present invention two.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described.Obviously, described embodiment is
Section Example of the invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
First the relevant technologies mentioned in this specification are introduced as follows before introducing embodiment:
TTS(Text to Speech, text-to-speech) it is a technology for converting text to voice, realize that machine can speak
Function, also referred to as speech synthesis (Synthesis).Speech synthesis technique is generally divided into parameter synthesis and splicing synthesis, wherein
Splicing synthesis be also with a kind of at most most mature technologies, by the way that the corresponding audio files of text is spliced, adjustment pause and transition in rhythm or melody and
It is one section of complete voice by word speed.In seat reservation system, market broadcast, the fields such as telecommunications bank customer service it is most widely used.
ASR(Automatic Speech Recognition, automatic speech recognition) it is a kind of to be converted to the sound of people
One technology of text realizes that the function that machine can be listened, target are that the vocabulary Content Transformation in the voice by the mankind is to calculate
Machine readable input, such as key, binary coding or character string etc..
MRCP(Media Resource Control Protocol, Media Resource Control Protocol), it is a support access
The agreement of media resource on network.Its typical case is exactly TTS and ASR.There are two versions for MRCP agreement, and wherein V1 editions make
Media resource negotiation is carried out with RTSP agreement, V2 editions then use the Session Initiation Protocol based on TCP.UniMRCP is the open source of MRCP agreement
It realizes, it supports two versions of V1 and V2
RTSP(Real Time Streaming Protocol), RFC2326, real time streaming transport protocol is ICP/IP protocol body
An application layer protocol in system, the IETF RFC standard submitted by Columbia University, Netscape and RealNetworks company.
The protocol define one-to-many applications how effectively to transmit multi-medium data by IP network.RTSP is architecturally
On RTP and RTCP, it completes data transmission using TCP or UDP.
Specific embodiment is described below, embodiment one:
Process step as shown in Figure 1, the present invention provides a kind of unattended intelligent phone inquiry methods of field of securities, use
In realizing ASR and TTS function in CTI system, the method and step of specific implementation is as follows:
Step 1, user puts through phone, the CTI system module automatic-answering back device inlet wire, and plays welcome voice.
When user puts through phone, the CTI system module automatic-answering back device inlet wire, CTI system module passes through inlet wire phone road
By Condition node establish user to the Channel A of CTI system module, play after call connection and automatically pre-
The welcome voice of typing CTI system module；CTI system module is by Session variable and SIP information preservation to Channel simultaneously
In A.
Step 2, the voice input of the CTI system module monitoring users.User says problem according to IVR voice prompting,
Such as stock is looked into, look into expire-services time etc..
When the CTI system module automatic-answering back device inlet wire, the signaling process of SIP intercommunication is completed.CTI system module
The problem of IVR plug-in unit voice prompting user says oneself, such as stock is looked into, the expire-services time is looked into, turns artificial etc..Voice prompting
After finishing, when receiving preset SIP status code is 200, CTI system module modifies the Status in Session variable
Value is Ready, executes snoop-operations and monitors the voice input of user.
Step 3, the CTI system module obtains and saves the voice of user's input, and CTI system module sends out the voice
It send to MRCPServer server, the MRCPServer server carries out voice, semantics recognition to the voice, described in acquisition
The crucial character/word of voice feeds back to CTI system module.
As shown in Fig. 2, the CTI system module by Action node load Type in the Session variable and
The value of Data obtains the VoP of Channel A and sub-process record session is called to save the voice data
Packet is the audio file on local disk；The SIP information of VoP and Channel A are imported Mod_ by CTI system module
Unimrcp module.
The Mod_unimrcp module according to received Channel A SIP information, call CTI system module
MRCPClient client is initiated to request to the MRCPServer server, completes the signaling process of SIP intercommunication, establishes CTI
For system module to the Channel B of MRCPServer server, receiving preset SIP status code to CTI system module is 200
When, Mod_unimrcp module connects Channel A with Channel B, sends the voice packet of user to by RTSP
MRCPServer server.
After the MRCPServer server receives VoP, ASR plug-in unit is called to read the VoP simultaneously
Voice, semantics recognition are carried out, obtains the crucial character/word of the VoP, such as look into stock, user said stock with Chinese
After title, CTI system module recognizes stock name that user says as keyword.The key set according to CTI system module
Keyword/Chinese word coding is the detect_speech_ that UTF8 is directed into the MRCPClient client by the weight ratio of character/word
In result variable.
Step 4, the CTI system module executes corresponding voice routing, calls according to the crucial character/word of acquisition
Query interface executes inquiry operation.
The shell script of the CTI system module executes corresponding voice according to detect_speech_result variate-value
Routing calls query interface to execute inquiry operation.The current share prices of the stock as needed for HTTP interface is called to inquire user.
Step 5, the CTI system module by Restful query interface calling be stored in database profession corresponding keyword/
Relevant textual information is sent to the MRCPServer server by the relevant textual information of word, CTI system module,
The relevant textual information is converted to reply voice and played out by MRCPServer server.
The CTI system module calls the phase for being stored in database profession corresponding crucial character/word by Restful query interface
The text parameter (such as stock real time price, amount of increase and amount of decrease etc.) for closing information is sent to the MRCPServer server；
After MRCPServer server receives the text parameter, calls TTS plug-in unit to identify the text parameter and synthesizes reply voice,
The reply voice of synthesis is sent to CTI system module by Channel B by MRCPServer server, then via
The reply voice is played to user by Channel A.
Step 6, after reply voice finishes, the MRCPServer server plays voice prompting, and inquiry user is
No needs continue to service, and the CTI system module continues the voice input of monitoring users.
After reply voice finishes, the MRCPClient client is destroyed in detect_speech_result variable
UTF8, the MRCPServer server sends voice prompting, inquires whether the user needs to continue to service.Voice prompting plays
After the CTI system module continue the voice inputs of monitoring users.
Step 7, step 2-6 is repeated, until the CTI system module is more than that default listening period does not hear voice
It inputs, then CTI system module automatic hand-up.
If when the voice input for once again listening for user in step 6, system repeats steps 2-6 is defeated to the voice of user
Enter to carry out voice, semantic analysis and plays reply voice.If user does not once again listen for user's in preset listening period
Voice input, then CTI system module automatic hand-up, terminates call.
For black phone customer service system, after user puts through phone, need to extract the voice prompting of big section, then root
The corresponding number key of choosing is pressed according to voice prompting, the selection of a service level is completed, into next level.However, general common
Phone customer service system can have multiple service levels, and user often will pass through 3-5 level just if it is desired to the service that acquisition is wanted
It can reach.What is more, it is also necessary to input the numbers such as ID card No. or account in some level.Often a process is gone down
Come it is 1-2 minutes to be spent, if midway select or input mistake, user's more time can be delayed.Even commonly using specific
The user of phone customer service system, selection operation will also divide several steps to complete, complicated for operation.
As shown in figure 3, relative to black phone customer service system, after user puts through phone in the present invention, system automatic-answering back device,
And the voice prompting sound pre-recorded in advance is played automatically.For example, user's system of telephoning in can play, " hello, welcomes to send a telegraph
Quality product client service center ", then system will " this is intelligent sound customer service, please say your stock name to be inquired " TTS text
Information is converted to voice, and user will continue to hear, and " this is intelligent sound customer service, please say your stock name " to be inquired
Voice.It can also be realized relative to traditional recording for telephone present invention, it is only necessary to one section of recording is saved in systems, and it is sharp
Voice is converted to the text information of TTS, flexibly can play different welcome voices for different user.
After user says inquiry content, system carries out voice, semantics recognition to voice, extracts crucial character/word and carries out
Inquiry, is converted to voice broadcast to user for query result.For example, user says " safety bank share price ", system extracts key
Word " safety bank ", " share price ", system is according to " safety bank ", the reality of " share price " the two keyword queries to its safety bank
When share price be 27.00, system generate text " safety bank, current share prices 27.00 " are simultaneously converted to voice broadcast to user.
The present invention is directed to realize ASR and TTS function using CTI system, a kind of unmanned value suitable for field of securities is invented
Smart phone inquiry method is kept, passive and cumbersome selection service option obtains when changing user using black phone customer service
Service gets rid of user and uses dependence when network customer service to network service.It more intelligently, is efficiently asked to be provided for user
Service is ask, important work is played to the intelligent management of client and the service of higher efficiency for telemarketing and customer service team for enterprise
With and application value.
1. realizing that phone inquiry is unattended substantially, it is only necessary to it is equipped with a small amount of contact staff and handles a small amount of manual service,
Greatly reduce customer service cost of labor.
2. realizing the service of user self-help express query, user is not required to clothes required for passively selecting according to voice prompting
Business, and proposition its demand for services that can be autonomous, system are specifically replied directly against particular problem, specific aim is extremely strong.Significantly
The service rate and service quality of service system are improved, brings more smooth, comfortable service experience to user.
3. realize the diversified intelligent Service of telephone system, even if in the case where user services without network, it still can be with
Intelligent query service is obtained, accessible inquiry is realized, better service guarantee is provided.
In view of this, the present invention can be provided for user can more intelligent quick inquiry service, be enterprise for phone battalion
It sells and customer service team is to the intelligent management of client and the service of higher efficiency plays an important role and application value.
Embodiment two:
System framework figure as shown in Figure 4, the present invention is based on described method provide a kind of unattended intelligent of field of securities electricity
Interrogation system is talked about, the system comprises as follows:
CTI system module is used for automatic-answering back device inlet wire, carries out call connection by inlet wire phone Route establishment Channel A；And
By Session variable and SIP information preservation into Channel A；The Status value of Session variable is modified, is executed default
Voice in listening period, which inputs, to be monitored；It obtains the VoP of Channel A and calls sub-process record session
Saving the VoP is the audio file on local disk；VoP and SIP information are imported into Mod_unimrcp
Module simultaneously establishes the Channel B with MRCPServer server by MRCPClient client；Obtain MRCPServer clothes
Device be engaged in the crucial character/word of VoP progress voice, semantic analysis generation, is stored in MRCPClient client
In detect_speech_result variable, and the corresponding voice routing of the crucial character/word is executed, calls Restful inquiry
Interface executes corresponding inquiry operation, and the text parameter for obtaining the relevant information of corresponding crucial character/word in database is sent to
MRCPServer server；The reply voice that MRCPServer server returns is played into user by Channel A；It plays
It finishes reply voice, continues monitoring users and whether input voice until being more than default listening period, then automatic hand-up.
The wherein MRCPClient client is called for Mod_unimrcp module, is issued to MRCPServer server
Request, complete SIP intercommunication signaling process, establish CTI system module to MRCPServer server Channel B；For
UTF8 is loaded onto detect_speech_result variable；After reply voice finishes, detect_speech_ is destroyed
UTF8 in result variable.
The Mod_unimrcp module, after the signaling process according to the completion SIP intercommunication of SIP information, described in calling
MRCPClient client establishes the CTI system module to the Channel B of the MRCPServer server；In CTI system
System module receive SIP status code be 200 OK when, Channel A is connected with Channel B, the voice packet of user is passed through
RTSP is sent to MRCPServer server.
MRCPServer server calls ASR plug-in unit to read the VoP for obtaining the VoP
Voice, semantics recognition are carried out, the crucial character/word of the VoP is obtained, according to the weight ratio of the crucial character/word of setting,
It is that UTF8 is imported in the MRCPClient client detect_speech_result variable by keyword/Chinese word coding；It is described
MRCPServer server obtains the text parameter of the CTI system module polls, and TTS plug-in unit is called to identify the text parameter
And reply voice is synthesized, and the reply voice of synthesis is back to by CTI system module by Channel B, it will via Channel A
The reply voice plays, and reply voice finishes, and sends voice prompting and asks whether to continue to service.
Database, for providing Restful query interface for the CTI system module according to detect_speech_
UTF8 in result variable is inquired and is obtained the text parameter of relevant information.
Based on above system, the present invention also provides a kind of unattended intelligent phone interrogation system of field of securities dresses
It sets, the system and device includes the following:
CTI system device is used for automatic-answering back device inlet wire, carries out call connection by inlet wire phone Route establishment Channel A；And
By Session variable and SIP information preservation into Channel A；The Status value of Session variable is modified, is executed default
Voice in listening period, which inputs, to be monitored；It obtains the VoP of Channel A and calls sub-process record session
Saving the VoP is the audio file on local disk；The SIP information of VoP and Channel A are imported
Mod_unimrcp device simultaneously establishes the Channel with MRCPServer server unit by MRCPClient client terminal device
B；The crucial character/word that MRCPServer server unit carries out voice, semantic analysis generation to VoP is obtained, is stored in
In the detect_speech_result variable of MRCPClient client terminal device, and execute the corresponding language of the crucial character/word
Sound routing, calls query interface to execute corresponding inquiry operation, obtains the text of the relevant information of corresponding crucial character/word in database
This parameter is sent to MRCPServer server unit；The reply voice that MRCPServer server unit returns is passed through
Channel A plays to user；Reply voice is finished, the voice input of monitoring users is continued, until being more than default monitor
Time, then automatic hand-up.
The wherein MRCPClient client terminal device is called for Mod_unimrcp device, to MRCPServer server
Device issues request, completes the signaling process of SIP intercommunication, establishes CTI system device to MRCPServer server unit
Channel B；For UTF8 to be loaded onto detect_speech_result variable；After reply voice finishes, destroy
UTF8 in detect_speech_result variable.
The Mod_unimrcp device, after the signaling process according to the completion SIP intercommunication of SIP information, described in calling
MRCPClient client terminal device establishes the CTI system module to the Channel B of the MRCPServer server unit；
When it is 200 OK that CTI system module, which receives preset SIP status code, Channel A is connected with Channel B, will be used
The voice packet at family is sent to MRCPServer server unit by RTSP.
MRCPServer server unit calls ASR plug-in unit to read the voice number for obtaining the VoP
Voice, semantics recognition are carried out according to packet, the crucial character/word of the VoP is obtained, according to the weight of the crucial character/word of setting
Than being that UTF8 imports the MRCPClient client terminal device detect_speech_result variable by keyword/Chinese word coding
In；The MRCPServer server unit obtains the text parameter of the CTI system module polls, calls the identification of TTS plug-in unit
The text parameter simultaneously synthesizes reply voice, and the reply voice of synthesis is back to CTI system module by Channel B, warp
The reply voice is played by Channel A, reply voice finishes, and sends voice prompting and asks whether to continue to service.
Data library device, for providing query interface for the CTI system module according to detect_speech_result
UTF8 in variable is inquired and is obtained the text parameter of relevant information.
It further include computer readable storage means, central processing unit, bus；The computer readable storage means are in
Central processor and CTI system device, MRCPClient client terminal device, Mod_unimrcp device, MRCPServer server dress
It sets, data library device is attached by bus；The computer readable storage means are stored with a plurality of operational order for center
Processor calls, and the central processing unit executes the operational order and realizes method described in the specification.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
The apparatus embodiments described above are merely exemplary, can be designed to integrated equipment, be also possible to group
A set of equipment is synthesized, may be distributed over multiple network units.Can select according to the actual needs part therein or
Whole modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not the case where paying creative labor
Under, it can it understands and implements.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software and required general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art its still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the range for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. the unattended intelligent phone inquiry method of field of securities, method and step are as follows:
Step 1, user puts through phone, the CTI system module automatic-answering back device inlet wire；
Step 2, the voice input of the CTI system module monitoring users；
Step 3, the CTI system module obtains the voice input of user, and the voice is sent to by CTI system module
MRCPServer server, the MRCPServer server carry out voice, semantics recognition to the voice, obtain the voice
Crucial character/word feed back to CTI system module；
Step 4, the CTI system module executes corresponding voice routing, calls inquiry according to the crucial character/word of acquisition
Interface executes inquiry operation；
Step 5, the CTI system module calls the correlation text for being stored in database profession corresponding crucial character/word by query interface
Relevant textual information is sent to the MRCPServer server by this information, CTI system module, and MRCPServer server will
The relevant textual information is converted to reply voice and plays out；
Step 6, reply voice finishes, and the MRCPServer server plays whether voice prompting continues to service, described
CTI system module continues the voice input of monitoring users；
Step 7, step 2-6 is repeated, until the CTI system module is more than that not hear voice defeated for default listening period
Enter, then CTI system module automatic hand-up.
2. the unattended intelligent phone inquiry method of field of securities according to claim 1, it is characterised in that the step 1
It include: when user puts through phone, the CTI system module automatic-answering back device inlet wire；CTI system module is routed by inlet wire phone
Condition node establishes user to the Channel A of CTI system module, carries out call connection；And by Session variable and
SIP information preservation is into Channel A.
3. the unattended intelligent phone inquiry method of field of securities according to claim 2, it is characterised in that the step 2
It include: the signaling process of SIP intercommunication to be completed, when receiving preset SIP shape after the CTI system module automatic-answering back device inlet wire
When state code, it is Ready that CTI system module, which modifies the Status value in Session variable, and CTI system module continues to execute default
Voice routing monitoring users voice input.
4. the unattended intelligent phone inquiry method of field of securities according to claim 3, it is characterised in that the step 3
Include: the value of Type and Data that the CTI system module is loaded by Action node in the Session variable, obtains
The VoP of all user's inputs of Channel A；VoP and SIP information are imported Mod_ by CTI system module
Unimrcp module；
The Mod_unimrcp module according to received Channel A SIP information, call CTI system module
MRCPClient client is initiated to request to the MRCPServer server, completes the signaling process of SIP intercommunication, establishes CTI
System module to MRCPServer server Channel B, when CTI system module receives preset SIP status code, Mod_
Unimrcp module connects Channel A with Channel B, sends the voice packet of user to by RTSP
MRCPServer server；
After the MRCPServer server receives VoP, calls ASR plug-in unit to read the VoP and carry out
Voice, semantics recognition obtain the crucial character/word of the VoP, according to the weight ratio of the crucial character/word of setting, will close
Key character/word is encoded to UTF8 and is directed into the detect_speech_result variable of the MRCPClient client.
5. the unattended intelligent phone inquiry method of field of securities according to claim 4, it is characterised in that the step 3
Further include: the CTI system module loads the value of the Type and Data in the Session variable by Action node, and
It executes the VoP for calling sub-process record session to obtain all user's inputs of Channel A and saves as this earth magnetism
Audio file on disk.
6. the unattended intelligent phone inquiry method of field of securities according to claim 4 or 5, it is characterised in that the step
Rapid 4 include: the shell script of the CTI system module according to the corresponding voice of detect_speech_result variate-value execution
Routing calls query interface to execute inquiry operation.
7. the unattended intelligent phone inquiry method of field of securities according to claim 6, it is characterised in that the step 5
It include: that the query interface calls the text parameter for the relevant information for being stored in database profession corresponding crucial character/word to be sent to institute
State MRCPServer server；After MRCPServer server receives the text parameter, TTS plug-in unit is called to identify the text
Parameter simultaneously synthesizes reply voice, and the reply voice of synthesis is sent to CTI system by Channel B by MRCPServer server
Then module plays the reply voice via Channel A.
8. the unattended intelligent phone inquiry method of field of securities according to claim 7, it is characterised in that the step 6
It include: that reply voice finishes, the MRCPClient client is destroyed in detect_speech_result variable
UTF8, the MRCPServer server send whether voice prompting continues to service, and the CTI system module continues monitoring users
Voice input.
9. the unattended intelligent phone interrogation system of field of securities, system include the following:
CTI system module is used for automatic-answering back device inlet wire, carries out call connection by inlet wire phone Route establishment Channel A；And
By Session variable and SIP information preservation to Channel A；The Status value of Session variable is modified, is executed in default prison
It listens the voice in the time to input to monitor；It obtains the VoP of Channel A and sub-process record session is called to protect
Depositing the VoP is the audio file on local disk；VoP and SIP information are imported into Mod_unimrcp mould
Block simultaneously establishes the Channel B with MRCPServer server by MRCPClient client；Obtain MRCPServer service
The crucial character/word that device carries out voice to VoP, semantic analysis generates, is stored in MRCPClient client
In detect_speech_result variable, and the corresponding voice routing of the crucial character/word is executed, query interface is called to execute
Corresponding inquiry operation, the text parameter for obtaining the relevant information of corresponding crucial character/word in database are sent to MRCPServer
Server；The reply voice that MRCPServer server returns is played into user by Channel A；Finish reply language
Sound continues monitoring users and whether inputs voice until being more than default listening period, then automatic hand-up；
The wherein MRCPClient client is called for Mod_unimrcp module, is asked to the sending of MRCPServer server
Ask, complete SIP intercommunication signaling process, establish CTI system module to MRCPServer server Channel B；For inciting somebody to action
UTF8 is loaded onto detect_speech_result variable；After reply voice finishes, detect_speech_ is destroyed
UTF8 in result variable；
The Mod_unimrcp module, after the signaling process according to the completion SIP intercommunication of SIP information, described in calling
MRCPClient client establishes the CTI system module to the Channel B of the MRCPServer server；In CTI system
When system module receives preset SIP status code, Channel A is connected with Channel B, the voice packet of user is passed through
RTSP is sent to MRCPServer server；
MRCPServer server calls ASR plug-in unit to read the VoP and carries out for obtaining the VoP
Voice, semantics recognition obtain the crucial character/word of the VoP, according to the weight ratio of the crucial character/word of setting, will close
Key character/word is encoded to UTF8 and imports in the MRCPClient client detect_speech_result variable；It is described
MRCPServer server obtains the text parameter of the CTI system module polls, and TTS plug-in unit is called to identify the text parameter
And reply voice is synthesized, and the reply voice of synthesis is sent to by CTI system module by Channel B, it will via Channel A
The reply voice plays, and reply voice finishes, and sends voice prompting and asks whether to continue to service；
Database, for providing query interface for the CTI system module according in detect_speech_result variable
UTF8 is inquired and is obtained the text parameter of relevant information.
10. the unattended intelligent phone interrogation system device of field of securities, system and device include the following:
CTI system device is used for automatic-answering back device inlet wire, carries out call connection by inlet wire phone Route establishment Channel A；And
By Session variable and SIP information preservation to Channel A；The Status value of Session variable is modified, is executed in default prison
It listens the voice in the time to input to monitor；It obtains the VoP of Channel A and sub-process record session is called to protect
Depositing the VoP is the audio file on local disk；VoP and SIP information are imported into Mod_unimrcp dress
It sets and passes through the foundation of MRCPClient client terminal device with the Channel B of MRCPServer server unit；It obtains
The crucial character/word that MRCPServer server unit carries out voice to VoP, semantic analysis generates, is stored in
In the detect_speech_result variable of MRCPClient client terminal device, and execute the corresponding language of the crucial character/word
Sound routing, calls query interface to execute corresponding inquiry operation, obtains the text of the relevant information of corresponding crucial character/word in database
This parameter is sent to MRCPServer server unit；The reply voice that MRCPServer server unit returns is passed through
Channel A plays to user；Reply voice is finished, the voice input of monitoring users is continued, until being more than default monitor
Time, then automatic hand-up；
The wherein MRCPClient client terminal device is called for Mod_unimrcp device, to MRCPServer server unit
Issue request, complete SIP intercommunication signaling process, establish CTI system device to MRCPServer server unit Channel
B；For UTF8 to be loaded onto detect_speech_result variable；After reply voice finishes, detect_ is destroyed
UTF8 in speech_result variable；
The Mod_unimrcp device, after the signaling process according to the completion SIP intercommunication of SIP information, described in calling
MRCPClient client terminal device establishes the CTI system module to the Channel B of the MRCPServer server unit；
When CTI system module receives preset SIP status code, Channel A is connected with Channel B, by the voice of user
Packet is sent to MRCPServer server unit by RTSP；
MRCPServer server unit calls ASR plug-in unit to read the VoP for obtaining the VoP
Voice, semantics recognition are carried out, the crucial character/word of the VoP is obtained, according to the weight ratio of the crucial character/word of setting,
It is that UTF8 is imported in the MRCPClient client terminal device detect_speech_result variable by keyword/Chinese word coding；
The MRCPServer server unit obtains the text parameter of the CTI system module polls, calls described in the identification of TTS plug-in unit
Text parameter simultaneously synthesizes reply voice, and the reply voice of synthesis is sent to CTI system module by Channel B, via
Channel A plays the reply voice, and reply voice finishes, and sends voice prompting and asks whether to continue to service；
Data library device, for providing query interface for the CTI system module according to detect_speech_result variable
In UTF8 inquire and obtain the text parameter of relevant information；
It further include computer readable storage means, central processing unit, bus；The same centre of computer readable storage means
Manage device and CTI system device, MRCPClient client terminal device, Mod_unimrcp device, MRCPServer server unit,
Data library device is attached by bus；The computer readable storage means are stored with a plurality of operational order for central processing
Device calls, and the central processing unit executes the operational order and realizes method described in claim 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810903110.7A CN109040482A (en) | 2018-08-09 | 2018-08-09 | The unattended intelligent phone inquiry method, system and device of field of securities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810903110.7A CN109040482A (en) | 2018-08-09 | 2018-08-09 | The unattended intelligent phone inquiry method, system and device of field of securities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109040482A true CN109040482A (en) | 2018-12-18 |
Family
ID=64632555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810903110.7A Pending CN109040482A (en) | 2018-08-09 | 2018-08-09 | The unattended intelligent phone inquiry method, system and device of field of securities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040482A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110010124A (en) * | 2019-04-09 | 2019-07-12 | 深圳平安综合金融服务有限公司上海分公司 | Equipment and the call method of inspection are examined in call |
| CN110457684A (en) * | 2019-07-15 | 2019-11-15 | 广州九四智能科技有限公司 | The semantic analysis of smart phone customer service |
| CN110769124A (en) * | 2019-10-30 | 2020-02-07 | 国网江苏省电力有限公司镇江供电分公司 | Electric power marketing customer communication system |
| CN111508467A (en) * | 2020-04-13 | 2020-08-07 | 湖南声广信息科技有限公司 | Audio splicing method for host of music broadcasting station |
| CN111556201A (en) * | 2020-05-08 | 2020-08-18 | 北京小米松果电子有限公司 | Method, device and storage medium for intelligently answering incoming call |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10190844A (en) * | 1996-12-27 | 1998-07-21 | Mitsubishi Electric Corp | Information processing unit management system |
| US6154526A (en) * | 1996-12-04 | 2000-11-28 | Intellivoice Communications, Inc. | Data acquisition and error correcting speech recognition system |
| CN1700714A (en) * | 2005-05-24 | 2005-11-23 | 陈妍慧 | System and method for implementing telephone voice service automatically |
| CN105244029A (en) * | 2015-08-28 | 2016-01-13 | 科大讯飞股份有限公司 | Voice recognition post-processing method and system |
-
2018
- 2018-08-09 CN CN201810903110.7A patent/CN109040482A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6154526A (en) * | 1996-12-04 | 2000-11-28 | Intellivoice Communications, Inc. | Data acquisition and error correcting speech recognition system |
| JPH10190844A (en) * | 1996-12-27 | 1998-07-21 | Mitsubishi Electric Corp | Information processing unit management system |
| CN1700714A (en) * | 2005-05-24 | 2005-11-23 | 陈妍慧 | System and method for implementing telephone voice service automatically |
| CN105244029A (en) * | 2015-08-28 | 2016-01-13 | 科大讯飞股份有限公司 | Voice recognition post-processing method and system |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110010124A (en) * | 2019-04-09 | 2019-07-12 | 深圳平安综合金融服务有限公司上海分公司 | Equipment and the call method of inspection are examined in call |
| CN110457684A (en) * | 2019-07-15 | 2019-11-15 | 广州九四智能科技有限公司 | The semantic analysis of smart phone customer service |
| CN110769124A (en) * | 2019-10-30 | 2020-02-07 | 国网江苏省电力有限公司镇江供电分公司 | Electric power marketing customer communication system |
| CN110769124B (en) * | 2019-10-30 | 2020-11-06 | 国网江苏省电力有限公司镇江供电分公司 | Electric power marketing customer communication system |
| CN111508467A (en) * | 2020-04-13 | 2020-08-07 | 湖南声广信息科技有限公司 | Audio splicing method for host of music broadcasting station |
| CN111556201A (en) * | 2020-05-08 | 2020-08-18 | 北京小米松果电子有限公司 | Method, device and storage medium for intelligently answering incoming call |
| CN111556201B (en) * | 2020-05-08 | 2021-06-29 | 北京小米松果电子有限公司 | Method, device and storage medium for intelligently answering incoming call |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109040482A (en) | The unattended intelligent phone inquiry method, system and device of field of securities | |
| CN106202301B (en) | A kind of intelligent response system based on deep learning | |
| CN111541821B (en) | Telephone customer service system and telephone customer service flexible switching method | |
| CN110891124B (en) | System for artificial intelligence pick-up call | |
| CN109413286B (en) | Intelligent customer service voice response system and method | |
| CN109873909B (en) | Voice calling method, device and equipment and computer storage medium | |
| CN109977218B (en) | A kind of automatic answering system and method applied to session operational scenarios | |
| WO2019201202A1 (en) | Call handling method and apparatus, server, storage medium, and system | |
| CN111885273A (en) | Man-machine cooperation controllable intelligent voice outbound method and intelligent outbound robot platform | |
| CN111131638A (en) | Intelligent outbound voice robot system and outbound method | |
| US8417523B2 (en) | Systems and methods for interactively accessing hosted services using voice communications | |
| CN101917524B (en) | Authentification information interacting method triggered by call center and orienting mobile Internet cellphone terminals | |
| JP2003507908A (en) | Method and apparatus for selectively presenting media options to a multimedia call center client | |
| CN109417583A (en) | It is a kind of by audio signal real time transcription be text system and method | |
| CN108777751A (en) | A kind of call center system and its voice interactive method, device and equipment | |
| US20100158204A1 (en) | Indexing recordings of telephony sessions | |
| AU2004310642A1 (en) | Multi-platform capable inference engine and universal grammar language adapter for intelligent voice application execution | |
| CN109327629A (en) | A kind of artificial intelligent voice navigation data processing method | |
| CN109995953A (en) | A kind of system and method for intelligence electricity pin | |
| CN109040481A (en) | The automatic error-correcting smart phone inquiry method, system and device of field of securities | |
| CN109005190B (en) | Method for realizing full duplex voice conversation and page control on webpage | |
| CN112040073A (en) | Intelligent directory assistance server, directory assistance system and directory assistance method | |
| CN113645124B (en) | System and method for pushing social platform information through intelligent voice interaction platform | |
| CN112185383A (en) | Processing method and system for customer service return visit | |
| CN111654581A (en) | Intelligent dialogue robot control method and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181218 |
|
| WD01 | Invention patent application deemed withdrawn after publication |