CN107749931A - Method, system, equipment and the storage medium of interactive voice answering - Google Patents
Method, system, equipment and the storage medium of interactive voice answering Download PDFInfo
- Publication number
- CN107749931A CN107749931A CN201710906603.1A CN201710906603A CN107749931A CN 107749931 A CN107749931 A CN 107749931A CN 201710906603 A CN201710906603 A CN 201710906603A CN 107749931 A CN107749931 A CN 107749931A
- Authority
- CN
- China
- Prior art keywords
- list
- voice synthesizing
- synthesizing server
- voice
- server
- 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
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003860 storage Methods 0.000 title abstract description 17
- 230000002194 synthesizing effect Effects 0.000 claims abstract description 78
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 18
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 18
- 239000002131 composite material Substances 0.000 claims abstract description 11
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 238000013515 script Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 210000004027 cell Anatomy 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 244000187656 Eucalyptus cornuta Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 210000000352 storage cell Anatomy 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
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5183—Call or contact centers with computer-telephony arrangements
- H04M3/5191—Call or contact centers with computer-telephony arrangements interacting with the Internet
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/61—Network streaming of media packets for supporting one-way streaming services, e.g. Internet radio
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides the method for interactive voice answering, system, equipment and storage medium, including step to obtain the configuration information of all voice synthesizing servers and be recorded in first list；Obtain user speech request；The occupancy quantity of the language Composite service being currently currently being used of the voice synthesizing server recorded in renewal second list；One by one by the occupancy quantity of the voice synthesizing server in second list compared with the default connection upper limit threshold of the same voice synthesizing server in first list；The default connection upper limit threshold of the selection connection voice synthesizing server maximum with taking number differences provides a user phonetic synthesis service, to carry out interactive voice answering.By comparing the default connection upper limit threshold of TTS engine and taking quantity, select free quantity maximum TTS engine and TTS service is provided, so as to realize TTS flexible access interactive voice answerings, realize load balancing.
Description
Technical field
The present invention relates to field of computer technology, more particularly to one kind to be based on phonetic synthesis (Text to Speech, TTS)
Method, system, equipment and the storage medium of the interactive voice answering of service.
Background technology
There are many large enterprises extremely strong to call center's business demand at present, be concentrated mainly on finance, tourism, insurance
Etc. industry.Call center's business usually need to use interactive voice answering (Interactive Voice Response,
IVR).IVR provides a kind of powerful phone automation services, when IVR is used in call center, is generally divided into preposition with after
Put, preposition IVR is that voice is introduced into IVR processing, and manual position is just transferred in the case where that can not solve customer issue, rearmounted
IVR refers to that IVR is in the position of balance with manual position, can not manually meet client to enter when talking about and turn IVR.In ivr, generally need
To use TTS service.TTS is by text, such as help file or webpage, is converted into natural-sounding output.This application
Use range is more and more extensive, and the telephone number report number of such as Best Tone Service, ecommerce have TTS application case.
As TTS and IVR technology reaches its maturity and both technologies be combined with each other, the IVR system of call center is big
Amount flow uses TTS service.The connection of existing ivr server and TTS engine is fixed, i.e., single ivr server pair
Single TTS service is answered, accordingly, it is possible to queuing phenomena can occur because some TTS engine usage amount exceedes rating data,
But simultaneously other TTS engine also has surplus resources.Especially as the raising of portfolio, TTS engine visit capacity is also fast
Speed increases, and has been further exacerbated by being lined up blocking, the situation of the wasting of resources.
Therefore how to realize load balancing that ivr server selectively accessed between TTS engine, multiserver, reach
Higher recognition effect and performance requirement turn into urgent problem to be solved.
The content of the invention
For the problems of the prior art, it is an object of the invention to provide a kind of method of interactive voice answering, it is
System, equipment and storage medium, can realize that ivr server selectively accesses TTS engine, solve concurrency it is big when can not
The problem of providing TTS service, realizes server load balancing.
The first aspect of the present invention provides a kind of method of interactive voice answering, comprises the following steps：S101, obtain institute
There is the configuration information of each voice synthesizing server in voice synthesizing server and be recorded in first list, configuration information
The default connection upper limit threshold of the language Composite service provided including voice synthesizing server；S102, obtain user speech request；
S103, the language being currently the currently being used synthesis clothes for monitoring and updating in real time the voice synthesizing server recorded in second list
The occupancy quantity of business；S104, one by one by the occupancy quantity of the voice synthesizing server in second list with it is same in first list
The default connection upper limit threshold of one voice synthesizing server is compared；S105, the default connection upper limit threshold of selection connection are with accounting for
Phonetic synthesis service is provided a user with the maximum voice synthesizing server of number differences, to carry out interactive voice answering；
S106, the voice synthesizing server for being recorded in first list but being lacked in second list is added in second list；S107, when
When the default connection upper limit threshold of voice synthesizing server is less than or equal to take quantity, the voice corresponding to deletion from second list
Synthesis server；Circulate implementation steps S102 to S107.
Preferably, in step S105, when the language that multiple default connection upper limit thresholds and occupancy number differences maximum be present
During sound synthesis server, the multiple default connection upper limit thresholds of the selection connection voice synthesizing server maximum with taking number differences
Middle performance than highest voice synthesizing server, performance than by the network transmission speed of voice synthesizing server, CPU usage,
Memory usage COMPREHENSIVE CALCULATING obtains.
Preferably, in step s 103, according to the voice synthesizing server listed in second list, one by one in log file
The occupancy quantity of the language Composite service being currently currently being used of middle crawl voice synthesizing server, log file records each
The operation data of individual voice synthesizing server.
Preferably, in step S104, connection upper limit threshold will be preset corresponding to the voice synthesizing server in first list
It is worth, and quantity is taken corresponding to the voice synthesizing server in second list and is stored in a manner of key-value pair in a set,
By voice synthesizing server title or voice synthesizing server ID traversal set, with the pre- of more same voice synthesizing server
If upper limit threshold is connected with taking quantity.
Preferably, IP address and the end of the voice synthesizing server of selection are inquired about in step S105, in first list
Mouthful, to connect the voice synthesizing server of selection by Media Resource Control Protocol.
Preferably, by loading LUA script file implementation steps S101 to S107.
The second aspect of the present invention provides a kind of interactive voice answering system, and system includes：Logging modle, logging modle
For obtaining the configuration information of each voice synthesizing server in all voice synthesizing servers and being recorded in first list
In, configuration information includes the default connection upper limit threshold for the language Composite service that voice synthesizing server provides, and logging modle is more
The occupancy quantity of the language Composite service being currently currently being used of the voice synthesizing server recorded in new second list；Receive
Module, receiving module are used to obtain user speech request；Distribute module, distribute module are used for one by one by the voice in second list
The occupancy quantity of synthesis server and the default connection upper limit threshold of the same voice synthesizing server in first list are compared
Compared with the default connection upper limit threshold of the selection connection voice synthesizing server maximum with taking number differences, distribute module is second
The voice synthesizing server for being recorded in first list but being lacked in second list is added in list, when voice synthesizing server
When default connection upper limit threshold is less than or equal to take quantity, the voice synthesizing server corresponding to deletion from second list；Perform
Module, execution module provides a user phonetic synthesis service for connecting distribute module selection voice synthesizing server, to carry out
Interactive voice answering.
Preferably, when the voice synthesizing server that multiple default connection upper limit thresholds and occupancy number differences maximum be present
When, the multiple default connection upper limit thresholds of the distribute module selection connection voice synthesizing server maximum with taking number differences is neutral
Can be than highest voice synthesizing server, performance is than the network transmission speed, CPU usage, internal memory by voice synthesizing server
Occupancy COMPREHENSIVE CALCULATING obtains.
The third aspect of the present invention provides a kind of interactive voice answering equipment, including：Processor；Memory, wherein depositing
Contain the executable instruction of processor；Wherein, processor is configured to perform above-mentioned first aspect via executable instruction is performed
Interactive voice answering method the step of.
The fourth aspect of the present invention provides a kind of computer-readable recording medium, for storage program, it is characterised in that journey
The step of method of the interactive voice answering of above-mentioned first aspect is realized when sequence is performed.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Method, system, equipment and the storage medium of interactive voice answering provided by the present invention have following advantages：
The present invention selects free quantity most by comparing the default connection upper limit threshold of TTS engine and taking quantity
Big TTS engine provides TTS service, so that the connection of ivr server and TTS engine is no longer fixed, flexible allocation
Resource, solve the problems, such as that when concurrency is big TTS service can not be provided, reached the effect of load balancing.
The TTS engine that default connection upper limit threshold is less than or equal to take quantity is deleted in second list, to provide
The TTS service that source has been exhausted no longer is chosen to carry out service offer, so as to prevent queuing phenomena.
The TTS engine for being recorded in first list but being lacked in second list is added in second list, so that
It can be reentered in the TTS engine of release resource in next round circulation alternative.
The present invention realizes the flexible access of TTS engine by software approach, it is not necessary to any hardware is additionally added,
Former IVR system is not interfered with, is reduced expenses, simple operation.
Brief description of the drawings
The detailed description made by reading with reference to the following drawings to non-limiting example, further feature of the invention,
Objects and advantages will become more apparent upon.
Fig. 1 is the flow chart of the method for the interactive voice answering of one embodiment of the invention；
Fig. 2 is the detail flowchart of step S105 in Fig. 1；
Fig. 3 is the data flow schematic diagram of the method for the interactive voice answering of one embodiment of the invention；
Fig. 4 is the structural representation of the system of the interactive voice answering of one embodiment of the invention；
Fig. 5 is the structural representation of the equipment of the interactive voice answering of one embodiment of the invention；
Fig. 6 is the structural representation of the computer-readable recording medium of one embodiment of the invention.
Embodiment
Example embodiment is described more fully with referring now to accompanying drawing.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, these embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in one or more embodiments in any suitable manner.
In addition, accompanying drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical accompanying drawing mark in figure
Note represents same or similar part, thus will omit repetition thereof.Some block diagrams shown in accompanying drawing are work(
Can entity, not necessarily must be corresponding with physically or logically independent entity.These work(can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Due to being connected for current ivr server and TTS engine, accordingly, it is possible to can be due to some TTS engine
Usage amount exceedes rating data and queuing phenomena occurs, but simultaneously other TTS engine also has surplus resources.The present invention's
Embodiment is in order to solve the above-mentioned technical problem, there is provided a kind of method of interactive voice answering, by comparing TTS engine
Default connection upper limit threshold and occupancy quantity, select free quantity maximum TTS engine and TTS service is provided, so that
The connection of ivr server and TTS engine is no longer fixed, flexible allocation resource, has reached the effect of load balancing.
Fig. 1 is the flow chart of the method for the interactive voice answering of one embodiment of the invention.Fig. 3 is one embodiment of the invention
Interactive voice answering method data flow schematic diagram.
With reference to shown in Fig. 1 and Fig. 3, equipment that the method for the interactive voice answering that the embodiment of the present invention is provided is related to
Including several interactive voice answering servers, i.e. ivr server 200, number amoyese speech synthesis server, i.e. TTS engine
300, several TTS engines 300 form TTS engine cluster.Several ivr servers 200 pass through with several TTS engines 300
Wide area network, LAN or cordless communication network connection.When user 100 sends voice shape by wide area network or cordless communication network
The request of formula.After specific ivr server 200 receives user speech request, TTS engine is accessed, to carry out interaction to user 100
TTS service is provided during formula voice answer-back.In other embodiments, according to business scale and needs an IVR can also be set to take
Business device and several TTS engines.
As shown in figure 1, the method for the interactive voice answering that the embodiment of the present invention is provided comprises the following steps：
S101, the configuration information for obtaining voice synthesizing server are simultaneously recorded in first list.Step S101 is initialization
Step, first list is established in the database of ivr server 200, the first list is static list, i.e., first list not with
The step of the method for interactive voice answering circulation performs and dynamic updates.All TTS clothes in record clustering in first list
The configuration information for each TTS engine 300 being engaged in device 300.Configuration information includes the title or ID of TTS engine 300
Number, the default connection upper limit threshold for the TTS service that can be provided, IP address and port numbers etc..When configuration information occurs more
When changing or adding or delete TTS engine 300 in cluster, the data in first list are updated.
Following step S102 to S107 performs step for circulation.
S102, obtain user speech request.
In the present embodiment, several ivr servers 200 determine the specific of processing user speech request according to load-balancing algorithm
Ivr server 200.
S103, the language being currently currently being used for monitoring and updating in real time the voice synthesizing server recorded in second list
Say the occupancy quantity of Composite service.
Second list is established in the database of ivr server 200, the second list is dynamic listing, i.e. second list
With interactive voice answering method the step of circulation perform and dynamic update.TTS engine 300 described in second list
For alternative TTS engine.When initial, the TTS engine 300 in first list is replicated into addition second list, can be used
The title of TTS engine 300 or ID identify the TTS engine 300.According to the TTS engine 300 listed in second list, by
One captures the occupancy quantity of the TTS service being currently currently being used of TTS engine 300 in log file, standby so as to update
The loading condition of TTS engine 300 of choosing.Log file records the operation data of each TTS engine 300, log file quilt
It is stored in each TTS engine 300, is independently updated by each TTS engine 300, or log file is stored in
In ivr server 200, ivr server 200 is periodically fed back by heartbeat to be obtained.
S104, the same TTS in the occupancy quantity of the TTS engine 300 in second list and first list is taken one by one
The default connection upper limit threshold of business device 300 is compared.The mode compared can be by the TTS engine in second list
300 title or ID finds the TTS engine 300 in first list, calculates in the default connection of same TTS engine 300
Threshold value is limited with taking number differences.
Preferably, connection upper limit threshold, and second list will be preset corresponding to the TTS engine 300 in first list
In TTS engine 300 corresponding to take quantity be stored in a manner of key-value pair in a set, pass through TTS engine 300
Title or ID traversal set, with the default connection upper limit threshold of more same TTS engine 300 with taking quantity.Key-value pair is just
Be can according to corresponding to obtaining key a value a kind of data mode.Data are stored in one by way of key-value pair
In set, it is easy to program quick calling and computing, operational efficiency lifting.
S105, the default connection upper limit threshold of selection the connection TTS engine maximum with taking number differences provide a user
Phonetic synthesis service, to carry out interactive voice answering.
Fig. 2 is the detail flowchart of step S105 in Fig. 1.As shown in Fig. 2 first such as step S1051, by S104
Compare, select the default connection upper limit threshold TTS engine 300 maximum with taking number differences.
Preferably, such as step S1052, judge whether that multiple default connection upper limit thresholds are maximum with taking number differences
TTS engine 300, as exist it is multiple it is default connection upper limit thresholds with take number differences maximum TTS engines 300 if hold
Row step S1053, as performed step S1055 in the absence of if.Such as step S1053, multiple default connection upper limit thresholds are calculated with accounting for
With the performance ratio of the maximum TTS engine 300 of number differences, the performance accounts for than the network transmission speed by TTS engine, CPU
Obtained with rate, memory usage COMPREHENSIVE CALCULATING, such as below equation can be passed through：
Cap=a*NTR-b*CR-c*MR
Wherein Cap is performance ratio, and a, b, c is weighted value, and NTR is network transmission speed, and CR is CPU usage, and MR is interior
Deposit occupancy.Weighted value a, b, c can be set according to being actually needed, it can also be provided that 0.
Such as step S1054, performance is selected than highest TTS engine 300.
In other embodiments, when the TTS service that multiple default connection upper limit thresholds and occupancy number differences maximum be present
During device 300, other selection modes, such as polling TTS engine, or the TTS service that selection is most replied soon can also be taken
Device.But using further selecting TTS engine than by the way of by calculating performance in the present embodiment, can be further to money
Source carries out reasonable distribution, there is provided overall operational efficiency, realizes the further optimization of load balancing.
After TTS engine is selected, into step S1055, the TTS engine 300 of selection is inquired about in first list
IP address and port.IP address and port are used for the connection of subsequent step.
Such as step S1056, the TTS engine 300 of selection is connected by MRCP.Media Resource Control Protocol (Media
Resource Control Protocol, MRCP) it is a kind of communications protocol, it is various to client offer for voice server
Voice service (such as speech recognition and phonetic synthesis).After MRCP agreements, stand alone software business and application developers only need to be towards
MRCP interfaces write program, without regard to the difference between the speech engine product of different phonetic manufacturer, can be truly realized
Primary development, apply under a variety of environment, the speech engine of any support MRCP standards can be by Seamless integration- and calling.IVR
The mode that server 200 accesses TTS service can pass through MRCP interface mode.Pass through the selection that is obtained in step S1055
The IP address of TTS engine 300 and port, ivr server 200 access the TTS of the TTS engine 300 of selection using MRCP
Service.
After ivr server 200 is connected foundation with the data of TTS engine 300, current TTS engine 300 services to IVR
Device 200 provides TTS service, so as to which ivr server 200 provides a user TTS service, to carry out interactive voice answering.
S106, the TTS engine 300 for being recorded in first list but being lacked in second list is added in second list.
S107, when TTS engine 300 default connection upper limit threshold be less than or equal to take quantity when, from second list
TTS engine 300 corresponding to deletion.
Step S106 and step S107 is the step of being used to screen alternative TTS engine 300.Judge when in step S104
When the default connection upper limit threshold of current TTS engine 300 is less than or equal to take quantity, i.e., the resource of current TTS engine 300
Used up, then perform step S107 is deleted from second list corresponding to TTS engine 300 so that in subsequent cycle this
The TTS engine of TTS engine 300 no longer alternately.
Resource is discharged as TTS engine 300 completes service, in order to rejoin the TTS for having discharged resource
Server 300, step S106 is performed, the TTS for being recorded in first list but being lacked in second list is added in second list
Server 300.By such mode, in subsequent cycle, when performing step S103, the TTS of the addition can be reacquired
The occupancy quantity of the language Composite service being currently currently being used of server 300.If by comparing in step S104, judge
When the default connection upper limit threshold of the TTS engine 300 of the addition is less than or equal to take quantity, then step S107 deletions are continued executing with
The TTS engine 300.Therefore, alternative TTS engine 300 can be efficiently controlled by step S106 and S107 so that
The TTS engine 300 that resource is used up no longer is chosen, and the TTS engine 300 for discharging resource can reenter alternatively, have
Reasonable distribution and the scheduling of resource are carried out to effect.
It should be noted that step S105 can be carried out before step S106, S107, can also carry out simultaneously, or
Carried out after S106, S107.
In the present invention, IVR service systems are realized by FreeSWITCH softwares.FreeSWITCH is one and cross-platform opened
Source telephone switching plane, there is very strong retractility, it is intended to for the media of audio, video, word or any other form, there is provided
Route and interconnection communication protocol.FreeSWITCH can Proterozoic run on Windows, Max OS X, Linux, BSD and
Many 32/64 bit platforms such as solaris, it may be used as simple switching engine, a PBX, a WMG or matchmaker
Body supports IVR server etc..It supports SIP, the agreement such as H323, Skype, Google Talk, and can easily with it is various
The PBX system increased income such as sipXecs, Call Weaver, Bayonne, YATE and Asterisk etc. communicate.FreeSWITCH is abided by
Follow RFC and support many advanced SIP characteristics, such as presence, BLF, SLA and TCP, TLS and sRTP.It can also be used
Make a SBC and carry out transparent sip agent (proxy) to support other media such as T.38.
The IVR service accesses TTS of present invention method, i.e. step S101 to S107, by loading LUA script files reality
Apply.LUA is a compact script, and its purpose of design is in order to be embedded in application program, so as to be provided for application program
Flexible extension and customization function.LUA is write by standard C and formed, and can almost be compiled in all operating systems and platform,
Operation.It by way of LUA scripts, not be compiled, be loaded directly into running.Meanwhile by such mode, it is not required to
The load balancing hardware or professional exploitation is carried out to former IVR system that extra purchase is special are wanted, does not also interfere with former IVR systems
System, save cost, simple operation.
It can be seen that, the method for interactive voice answering provided by the present invention, pass through by the description to above-described embodiment
Compare the default connection upper limit threshold of TTS engine and take quantity, select the maximum TTS engine of free quantity and provide
TTS service, so that the connection of ivr server and TTS engine is no longer fixed, flexible allocation resource, solves concurrency
The problem of can not providing TTS service when big, the effect of load balancing is reached.
The TTS engine that default connection upper limit threshold is less than or equal to take quantity is deleted in second list, to provide
The TTS service that source has been exhausted no longer is chosen to carry out service offer, so as to prevent queuing phenomena, improves efficiency.
The TTS engine for being recorded in first list but being lacked in second list is added in second list, so that
It can be reentered in the TTS engine of release resource in next round circulation alternative.
The present invention realizes the flexible access of TTS engine by software approach, it is not necessary to any hardware is additionally added,
Former IVR system is not interfered with, is reduced expenses, simple operation.
It is above-mentioned mutual for realizing as shown in figure 4, the embodiment of the present invention also provides a kind of system of interactive voice answering
The method of dynamic formula voice answer-back.Specifically, the system 210 of interactive voice answering is arranged in ivr server 200, mutually
The system 210 of dynamic formula voice answer-back includes logging modle 201, receiving module 202, distribute module 203 and execution module 204.
Logging modle 201 is for obtaining the configuration information of each TTS engine 300 in all TTS engines 300 simultaneously
It is recorded in first list.Configuration information includes the default connection upper limit threshold for the TTS service that TTS engine 300 provides.Record
Module 201 updates the occupancy quantity of the TTS service being currently currently being used of the TTS engine 300 recorded in second list.
Receiving module 202 is used to obtain user speech request.
Distribute module 203 is used for the default connection upper limit threshold for comparing corresponding TTS engine 300 in first list one by one
It is poor with taking quantity with the occupancy quantity of the same TTS engine 300 in second list, the default connection upper limit threshold of selection connection
It is worth maximum TTS engine 300.Further, it is maximum with taking number differences when multiple default connection upper limit thresholds be present
During TTS engine 300, the multiple default connection upper limit thresholds of the selection connection of distribute module 203 TTS maximum with taking number differences
Performance is than highest TTS engine 300 in server 300.Performance is than the network transmission speed by voice synthesizing server, CPU
Occupancy, memory usage COMPREHENSIVE CALCULATING obtain.
Distribute module 203 is additionally operable to screen alternative TTS engine 300.Specifically, distribute module 203 is in second list
It is middle to add the TTS engine 300 for being recorded in first list but being lacked in second list, so as to realize the TTS for discharging resource
Server 300 rejoins alternatively.When the default connection upper limit threshold of TTS engine 300 is less than or equal to take quantity, distribution
Module 203 deleted from second list corresponding to TTS engine 300 so that the TTS engine 300 is no longer alternately
TTS engine.
Execution module 204 is used to connect the selection TTS engine 300 of distribute module 203, so as to realize the access of TTS service,
Phonetic synthesis service is provided a user, to carry out interactive voice answering.
The modules of the system 210 of the interactive voice answering of the embodiment of the present invention implement the side of interactive voice answering
The specific steps of method are as above to described in the method for interactive voice answering, here is omitted.
By the system of the interactive voice answering of the present invention, by the default connection upper limit threshold for comparing TTS engine
And quantity is taken, select free quantity maximum TTS engine and TTS service is provided, so that the access of TTS engine is not
Fix again, flexible allocation resource, solve the problems, such as that when concurrency is big TTS service can not be provided, reached the effect of load balancing
Fruit.
The TTS engine that default connection upper limit threshold is less than or equal to take quantity is deleted in second list, to provide
The TTS service that source has been exhausted no longer is chosen to carry out service offer, so as to prevent queuing phenomena, improves efficiency.
The TTS engine for being recorded in first list but being lacked in second list is added in second list, so that
It can be reentered in the TTS engine of release resource in next round circulation alternative.
The embodiment of the present invention also provides a kind of interactive voice answering equipment, including processor；Memory, wherein being stored with
The executable instruction of the processor；Wherein, the processor is configured to perform via the executable instruction is performed described
Interactive voice answering method the step of.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be implemented as following form, i.e.,：It is complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.), or hardware and software, can unite here
Referred to as " circuit ", " module " or " platform ".
The electronic equipment 600 according to the embodiment of the invention is described referring to Fig. 5.The electronics that Fig. 5 is shown
Equipment 600 is only an example, should not bring any restrictions to the function and use range of the embodiment of the present invention.
As shown in figure 5, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
Include but be not limited to：At least one processing unit 610, at least one memory cell 620, (including the storage of connection different platform component
Unit 620 and processing unit 610) bus 630, display unit 640 etc..
Wherein, the memory cell is had program stored therein code, and described program code can be held by the processing unit 610
OK so that the processing unit 610 perform described in the above-mentioned electronic prescription circulation processing method part of this specification according to this
The step of inventing various illustrative embodiments.For example, the step of processing unit 610 can perform as shown in fig. 1.
The memory cell 620 can include the computer-readable recording medium of volatile memory cell form, such as random access memory
Unit (RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
The memory cell 620 can also include program/practical work with one group of (at least one) program module 6205
Tool 6204, such program module 6205 includes but is not limited to：Operating system, one or more application program, other programs
Module and routine data, the realization of network environment may be included in each or certain combination in these examples.
Bus 630 can be to represent the one or more in a few class bus structures, including memory cell bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment communication interacted with the electronic equipment 600 can be also enabled a user to one or more, and/or with causing
Any equipment that the electronic equipment 600 can be communicated with one or more of the other computing device (such as router, modulation /demodulation
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 660 can be communicated by bus 630 with other modules of electronic equipment 600.Should
Understand, although not shown in the drawings, can combine electronic equipment 600 uses other hardware and/or software module, including it is but unlimited
In：Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage platform etc..
As described above, when performing above-mentioned interactive voice answering method by the interactive voice answering equipment of the present invention,
By comparing the default connection upper limit threshold of TTS engine and taking quantity, select the maximum TTS engine of free quantity and carry
For TTS service, so that the connection of ivr server and TTS engine is no longer fixed, flexible allocation resource, solve concurrent
The problem of TTS service can not be provided when measuring big, the effect of load balancing is reached.
The TTS engine that default connection upper limit threshold is less than or equal to take quantity is deleted in second list, to provide
The TTS service that source has been exhausted no longer is chosen to carry out service offer, so as to prevent queuing phenomena, improves efficiency.
The TTS engine for being recorded in first list but being lacked in second list is added in second list, so that
It can be reentered in the TTS engine of release resource in next round circulation alternative.
The embodiment of the present invention also provides a kind of computer-readable recording medium, and for storage program, described program is performed
The step of method of the above-mentioned interactive voice answerings of Shi Shixian.In some possible embodiments, various aspects of the invention
A kind of form of program product is also implemented as, it includes program code, when described program product is run on the terminal device
When, described program code is retouched for making the terminal device perform in the above-mentioned electronic prescription circulation processing method part of this specification
State according to the step of various illustrative embodiments of the invention.
With reference to shown in figure 6, the program product for being used to realize the above method according to the embodiment of the present invention is described
800, it can use portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as run on PC.However, the program product not limited to this of the present invention, in this document, readable storage medium storing program for executing can be with
Be it is any include or the tangible medium of storage program, the program can be commanded execution system, device either device use or
It is in connection.
Described program product can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any combination above.The more specifically example of readable storage medium storing program for executing is (non exhaustive
List) include：It is electrical connection, portable disc, hard disk, random access memory (RAM) with one or more wires, read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer-readable recording medium can include believing in a base band or as the data that a carrier wave part is propagated
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any beyond readable storage medium storing program for executing
Computer-readable recording medium, the computer-readable recording medium can send, propagate either transmit for being used by instruction execution system, device or device or
Person's program in connection.The program code included on readable storage medium storing program for executing can be transmitted with any appropriate medium, bag
Include but be not limited to wireless, wired, optical cable, RF etc., or above-mentioned any appropriate combination.
Can being combined to write the program operated for performing the present invention with one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., include routine
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
Perform on computing device, partly perform on a user device, the software kit independent as one performs, is partly calculated in user
Its upper side point is performed or performed completely in remote computing device or server on a remote computing.It is remote being related to
In the situation of journey computing device, remote computing device can pass through the network of any kind, including LAN (LAN) or wide area network
(WAN) user calculating equipment, is connected to, or, it may be connected to external computing device (such as utilize ISP
To pass through Internet connection).
As described above, when running the program in the computer-readable recording medium using external equipment, can also realize
The flexible access of TTS service, realize the load balancing of TTS engine.
Method, system, equipment and the storage medium of interactive voice answering provided by the present invention have following advantages：
By comparing the default connection upper limit threshold of TTS engine and taking quantity, the maximum TTS of free quantity is selected
Server provides TTS service, so that the connection of ivr server and TTS engine is no longer fixed, flexible allocation resource, solution
The problem of concurrency of having determined can not provide TTS service when big, has reached the effect of load balancing.
The TTS engine that default connection upper limit threshold is less than or equal to take quantity is deleted in second list, to provide
The TTS service that source has been exhausted no longer is chosen to carry out service offer, so as to prevent queuing phenomena, improves efficiency.
The TTS engine for being recorded in first list but being lacked in second list is added in second list, so that
It can be reentered in the TTS engine of release resource in next round circulation alternative.
The present invention realizes the flexible access of TTS engine by software approach, it is not necessary to any hardware is additionally added,
Former IVR system is not interfered with, is reduced expenses, simple operation.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to is assert
The specific implementation of the present invention is confined to these explanations.For general technical staff of the technical field of the invention,
On the premise of not departing from present inventive concept, some simple deduction or replace can also be made, should all be considered as belonging to the present invention's
Protection domain.
Claims (10)
- A kind of 1. method of interactive voice answering, it is characterised in that comprise the following steps：S101, the configuration information for obtaining each voice synthesizing server in all voice synthesizing servers are simultaneously recorded in first In list, the configuration information includes the default connection upper limit threshold for the language Composite service that the voice synthesizing server provides Value；S102, obtain user speech request；S103, the language being currently the currently being used conjunction for monitoring and updating in real time the voice synthesizing server recorded in second list Into the occupancy quantity of service；S104, one by one by the same phonetic synthesis in the occupancy quantity of the voice synthesizing server in second list and first list The default connection upper limit threshold of server is compared；S105, the selection connection default connection upper limit threshold voice synthesizing server maximum with the occupancy number differences to User provides phonetic synthesis service, to carry out interactive voice answering；S106, the voice synthesizing server for being recorded in first list but being lacked in second list is added in second list；S107, when the default connection upper limit threshold of voice synthesizing server is less than or equal to the occupancy quantity, from described Voice synthesizing server corresponding to being deleted in second list；Circulate implementation steps S102 to S107.
- 2. the method for interactive voice answering according to claim 1, it is characterised in thatIn step S105, closed when multiple default connection upper limit thresholds voice maximum with the occupancy number differences be present During into server, the multiple default connection upper limit thresholds of the selection connection phonetic synthesis maximum with the occupancy number differences takes Being engaged in device, performance is than highest voice synthesizing server, and the performance is than the network transmission speed by voice synthesizing server, CPU Occupancy, memory usage COMPREHENSIVE CALCULATING obtain.
- 3. the method for interactive voice answering according to claim 1, it is characterised in thatIn step s 103, according to the voice synthesizing server listed in the second list, captured one by one in log file The occupancy quantity of the language Composite service being currently currently being used of the voice synthesizing server, the log file record are every The operation data of one voice synthesizing server.
- 4. the method for interactive voice answering according to claim 1, it is characterised in thatIn step S104, connection upper limit threshold, and second will be preset corresponding to the voice synthesizing server in first list Quantity is taken corresponding to voice synthesizing server in list to be stored in a manner of key-value pair in a set, passes through phonetic synthesis Server name or voice synthesizing server ID travel through the set, with the default company of more same voice synthesizing server Connect upper limit threshold and the occupancy quantity.
- 5. the method for interactive voice answering according to claim 1 or 2, it is characterised in thatIP address and the port of the voice synthesizing server of selection are inquired about in step S105, in first list, to pass through matchmaker Body Resource Control protocols connect the voice synthesizing server of selection.
- 6. the method for interactive voice answering according to claim 1, it is characterised in thatImplement the step S101 to S107 by loading LUA script files.
- 7. a kind of interactive voice answering system, it is characterised in that the system includes：Logging modle, the logging modle are used to obtain each voice synthesizing server in all voice synthesizing servers Configuration information is simultaneously recorded in first list, and the configuration information includes the language synthesis clothes that the voice synthesizing server provides The default connection upper limit threshold of business, the voice synthesizing server recorded in logging modle renewal second list it is current The occupancy quantity of the language Composite service used；Receiving module, the receiving module are used to obtain user speech request；Distribute module, the distribute module are used for one by one by the occupancy quantity and first of the voice synthesizing server in second list The default connection upper limit threshold of same voice synthesizing server in list is compared, and selection connects the default connection upper limit The threshold value voice synthesizing server maximum with the occupancy number differences, the distribute module are added in second list and are recorded in The voice synthesizing server lacked in first list but in second list, when the default connection upper limit of voice synthesizing server When threshold value is less than or equal to the occupancy quantity, the voice synthesizing server corresponding to deletion from the second list；Execution module, the execution module provide a user voice for connecting the distribute module selection voice synthesizing server Composite service, to carry out interactive voice answering.
- 8. interactive voice answering system as claimed in claim 7, it is characterised in thatWhen multiple default connection upper limit thresholds and the voice synthesizing server of the occupancy number differences maximum be present, institute The multiple default connection upper limit thresholds of the distribute module selection connection phonetic synthesis maximum with the occupancy number differences is stated to take Being engaged in device, performance is than highest voice synthesizing server, and the performance is than the network transmission speed by voice synthesizing server, CPU Occupancy, memory usage COMPREHENSIVE CALCULATING obtain.
- A kind of 9. interactive voice answering equipment, it is characterised in that including：Processor；Memory, wherein being stored with the executable instruction of the processor；Wherein, the processor is configured to come any one of perform claim requirement 1 to 6 via the execution executable instruction Interactive voice answering method the step of.
- 10. a kind of computer-readable recording medium, for storage program, it is characterised in that power is realized when described program is performed Profit requires the step of method of the interactive voice answering any one of 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710906603.1A CN107749931A (en) | 2017-09-29 | 2017-09-29 | Method, system, equipment and the storage medium of interactive voice answering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710906603.1A CN107749931A (en) | 2017-09-29 | 2017-09-29 | Method, system, equipment and the storage medium of interactive voice answering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107749931A true CN107749931A (en) | 2018-03-02 |
Family
ID=61255977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710906603.1A Pending CN107749931A (en) | 2017-09-29 | 2017-09-29 | Method, system, equipment and the storage medium of interactive voice answering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107749931A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428840A (en) * | 2019-07-19 | 2019-11-08 | 平安科技（深圳）有限公司 | Implementation of load balancing, device and computer equipment in speech recognition system |
| CN110740212A (en) * | 2019-09-26 | 2020-01-31 | 北京淇瑀信息科技有限公司 | Call answering method and device based on intelligent voice technology and electronic equipment |
| CN111770236A (en) * | 2020-02-13 | 2020-10-13 | 北京沃东天骏信息技术有限公司 | Conversation processing method, device, system, server and storage medium |
| CN112527234A (en) * | 2020-11-05 | 2021-03-19 | 北京百度网讯科技有限公司 | Audio frame output method and device |
| CN113630613A (en) * | 2021-07-30 | 2021-11-09 | 出门问问信息科技有限公司 | Information processing method, device and storage medium |
| CN115148182A (en) * | 2021-03-15 | 2022-10-04 | 阿里巴巴新加坡控股有限公司 | Speech synthesis method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5715370A (en) * | 1992-11-18 | 1998-02-03 | Canon Information Systems, Inc. | Method and apparatus for extracting text from a structured data file and converting the extracted text to speech |
| CN101635745A (en) * | 2009-08-19 | 2010-01-27 | 中兴通讯股份有限公司 | Method and device for sharing load of multi-text voice transferring server |
| CN101677329A (en) * | 2008-09-18 | 2010-03-24 | 中兴通讯股份有限公司 | Comprehensive voice resource platform proxy server and its data processing method |
| CN101753558A (en) * | 2009-12-11 | 2010-06-23 | 安徽科大讯飞信息科技股份有限公司 | Distributed MRCP server load balancing system and balancing method thereof |
| CN105489216A (en) * | 2016-01-19 | 2016-04-13 | 百度在线网络技术（北京）有限公司 | Voice synthesis system optimization method and device |
| CN107026907A (en) * | 2017-03-30 | 2017-08-08 | 上海斐讯数据通信技术有限公司 | A kind of load-balancing method, load equalizer and SiteServer LBS |
-
2017
- 2017-09-29 CN CN201710906603.1A patent/CN107749931A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5715370A (en) * | 1992-11-18 | 1998-02-03 | Canon Information Systems, Inc. | Method and apparatus for extracting text from a structured data file and converting the extracted text to speech |
| CN101677329A (en) * | 2008-09-18 | 2010-03-24 | 中兴通讯股份有限公司 | Comprehensive voice resource platform proxy server and its data processing method |
| CN101635745A (en) * | 2009-08-19 | 2010-01-27 | 中兴通讯股份有限公司 | Method and device for sharing load of multi-text voice transferring server |
| CN101753558A (en) * | 2009-12-11 | 2010-06-23 | 安徽科大讯飞信息科技股份有限公司 | Distributed MRCP server load balancing system and balancing method thereof |
| CN105489216A (en) * | 2016-01-19 | 2016-04-13 | 百度在线网络技术（北京）有限公司 | Voice synthesis system optimization method and device |
| CN107026907A (en) * | 2017-03-30 | 2017-08-08 | 上海斐讯数据通信技术有限公司 | A kind of load-balancing method, load equalizer and SiteServer LBS |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428840A (en) * | 2019-07-19 | 2019-11-08 | 平安科技（深圳）有限公司 | Implementation of load balancing, device and computer equipment in speech recognition system |
| CN110740212A (en) * | 2019-09-26 | 2020-01-31 | 北京淇瑀信息科技有限公司 | Call answering method and device based on intelligent voice technology and electronic equipment |
| CN110740212B (en) * | 2019-09-26 | 2021-08-27 | 北京淇瑀信息科技有限公司 | Call answering method and device based on intelligent voice technology and electronic equipment |
| CN111770236A (en) * | 2020-02-13 | 2020-10-13 | 北京沃东天骏信息技术有限公司 | Conversation processing method, device, system, server and storage medium |
| CN112527234A (en) * | 2020-11-05 | 2021-03-19 | 北京百度网讯科技有限公司 | Audio frame output method and device |
| CN115148182A (en) * | 2021-03-15 | 2022-10-04 | 阿里巴巴新加坡控股有限公司 | Speech synthesis method and device |
| CN113630613A (en) * | 2021-07-30 | 2021-11-09 | 出门问问信息科技有限公司 | Information processing method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107749931A (en) | Method, system, equipment and the storage medium of interactive voice answering | |
| CN109032760A (en) | Method and apparatus for application deployment | |
| US9264289B2 (en) | Endpoint data centers of different tenancy sets | |
| US9722886B2 (en) | Management of cloud provider selection | |
| US8724795B1 (en) | Problem centric knowledge management tool for call center | |
| US20080040417A1 (en) | System and method for allocating workflow operations to a computing device | |
| CN101888320A (en) | Enhanced Network Adapter Framework | |
| US11714638B2 (en) | Availability level-based service management | |
| CN108989583A (en) | Method for testing pressure, system, electronic equipment and the storage medium of call center | |
| US10135981B2 (en) | Routing during communication of help desk service | |
| JP2022075546A (en) | Shared Enterprise Cloud Systems, Methods, Computing Devices | |
| US11281510B2 (en) | Intelligent scaling in microservice-based distributed systems | |
| JP2021517683A (en) | Workload management with data access awareness in a computing cluster | |
| CN109587356A (en) | Virtual-number call method, device, system, electronic equipment, storage medium | |
| CN109918146A (en) | Page generation method and device | |
| JP7561874B2 (en) | Discovering the Application Topology | |
| JP7564831B6 (en) | SYSTEM AND METHOD FOR ADDING CONTENT TO CONTACT CENTER INTERACTIONS - Patent application | |
| US20180246845A1 (en) | Virtualizing tcp/ip services with shared memory transport | |
| KR102714245B1 (en) | Communication with application flows in an integrated system | |
| US7499992B1 (en) | Association traversal translation for common information model | |
| US10769204B2 (en) | System and method for unsupervised discovery of similar audio events | |
| CN108718325A (en) | Telephone outbound call method, system, equipment and storage medium based on dynamic registration | |
| JP2021531562A (en) | Two-step calculation memoing for large-scale entity resolution | |
| US11943115B2 (en) | Locally debugging remote deployment of microservices | |
| US20240223706A1 (en) | Specialized Microbots in Contact Centers |
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: 20180302 |