CN102868836B - For real person talk skill system and its implementation of call center - Google Patents

For real person talk skill system and its implementation of call center Download PDF

Info

Publication number
CN102868836B
CN102868836B CN201210344584.5A CN201210344584A CN102868836B CN 102868836 B CN102868836 B CN 102868836B CN 201210344584 A CN201210344584 A CN 201210344584A CN 102868836 B CN102868836 B CN 102868836B
Authority
CN
China
Prior art keywords
words
seat
client
recording file
skill
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201210344584.5A
Other languages
Chinese (zh)
Other versions
CN102868836A (en
Inventor
吴益民
翁兵
李玉江
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
BEJING INFOBIRD SOFTWARE CO LTD
Original Assignee
BEJING INFOBIRD SOFTWARE CO LTD
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by BEJING INFOBIRD SOFTWARE CO LTD filed Critical BEJING INFOBIRD SOFTWARE CO LTD
Priority to CN201210344584.5A priority Critical patent/CN102868836B/en
Publication of CN102868836A publication Critical patent/CN102868836A/en
Application granted granted Critical
Publication of CN102868836B publication Critical patent/CN102868836B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention discloses a kind of real person talk skill system and its implementation.This real person talk skill system comprises client, switch, seat end, words art retrieval/playing module and words art database; Wherein talk about art retrieval/playing module respectively with seat end, talk about art database and be connected, seat end and client are by switch formation double-directional speech path; Seat end, according to the voice messaging receiving client, talks about art recording file by words art retrieval/playing module to words art database retrieval, to client terminal playing after retrieving required words art recording file.The present invention significantly can reduce the labour intensity of seat person, ensures the operating efficiency that seat person continues, and improves the labor productivity of call center seat person.

Description

For real person talk skill system and its implementation of call center
Technical field
The present invention relates to a kind of real person talk skill system, particularly relating to one is used in call center, recorded by broadcasting true man and realize the real person talk skill system of answer, also relating to this real person talk skill system by retrieving the method realizing real person talk skill recording answer simultaneously, belonging to call-center technology field.
Background technology
Along with the development that service trade is maked rapid progress, the enterprise in the industries such as telecommunications, bank, security, insurance is often equipped with special call center.These call centers, based on incoming call business, are called as customer service telephone traffic system.Being provided with to be beneficial to and improving service quality of it, increases customer satisfaction degree and loyalty.On the other hand, the sales department of enterprise, in order to increase income from sales, often needs to outcall promotion business.This call center based on call business is called as traffic marketing system.
No matter be customer service telephone traffic system or traffic marketing system, all need after connection client outside line, corresponding call forwarding to be carried out mutual to seat person's (also claiming seat end).In existing call-center application, for same business, the problem that client proposes is often substantially identical.Reduce workload to make seat person and ensure that the answer content of different seat person is basically identical, call center often makes unified words art scheme to FAQs, and adopts text mode to be prompted to seat person.Seat person, when answering client questions, first retrieves what these said art scheme, then reads the content retrieved according to prompting.
In a call in the heart, no matter be incoming call business or call business, the words art scheme of same business is all basically identical.Below, be briefly described as follows with the scene content in telemarketing process:
If 1. client says: " I needs to consider ", so corresponding answer can be:
" Mr. ×× (Miss), tease saying of, you tell that I will consider, and this only can not be to avoid me
" I wishes that you really can consider this thing, and me can be allowed to learn about, the mainly which aspect that you will consider is product quality, or after-sale service, or whether I leaked what has been said just now "
If 2. client says: " I temporarily not too needs, and may consider after a time again ", this situation is that client has purchase intention often, but not too clear and definite, or habitually delay, so corresponding answer can be:
" you are good, and what we discussed now seems to be exactly a decision "
If you say "Yes", that can be how
If you say "no", can change without any thing, tomorrow will be the same with today.
If you say "Yes" today, this is the benefit that you are about to obtain: 1 ... 2 ... 3 ... obviously agree more beneficial than being unable to say for certain, you say is that right
If 3. client says " market is depressed recently ", so corresponding answer can be
If 4. client says " budgetary not at us ", so corresponding answer can be ...
Can find out importance and the application model of words art scheme from above-mentioned scene, its Main Function is supplied to the response scheme that seat person tackles the situations such as client's question, query in advance.The subject matter existed in this process is: on the one hand, and need seat person repeatedly to repeat some and answer, the workload of seat person is very large; On the other hand, the answer constantly repeating identical content can allow seat person feel tired, is difficult to the effect ensureing marketing or service.
Summary of the invention
For the deficiency existing for prior art, technical problem to be solved by this invention is to provide one to be used in call center, by play true man record realize reply real person talk skill system and its implementation.Adopt this technical scheme can alleviate the work load of seat person, improve the operating efficiency of seat person.
For realizing above-mentioned goal of the invention, the present invention adopts following technical scheme:
A kind of real person talk skill system, is characterized in that:
Described real person talk skill system comprises client, switch, seat end, words art retrieval/playing module and words art database;
Described words art retrieval/playing module is connected with described seat end, described words art database respectively, and described seat end and described client form double-directional speech path by described switch;
Described seat end, according to the voice messaging receiving client, talks about art recording file by described words art retrieval/playing module to described words art database retrieval, to described client terminal playing after retrieving required words art recording file.
Wherein more preferably, described switch comprises barge module.
Wherein more preferably, described words art retrieval/playing module comprises sound identification module.
Wherein more preferably, described words art database comprises words art search library and true man's sound bank, there are mapping relations between the search index in described words art search library and the words art recording file in described true man's sound bank.
Realize a method for real person talk skill, realize based on above-mentioned real person talk skill system, it is characterized in that:
When client asks a question to seat end, described seat end is by the words art retrieval/playing module words art recording file that search problem is corresponding in words art database; If words art recording file exists, then talk about art recording file directly to described in described client terminal playing, described words art recording file plays to described seat end simultaneously; If words art recording file does not exist, described seat end is directly conversed with described client and is answered a question, and starts Recording Process simultaneously and generates words art recording file in real time, and associate this words art recording file stored in described words art database with key to the issue word.
Wherein more preferably, described seat end records the words art recording file of oneself in advance in described words art database, and and sets up mapping relations between the search index in words art search library.
Wherein more preferably, in described words art retrieval/playing module, sound identification module is set, by the subject of question of client described in described sound identification module identification, described words art retrieval/playing module directly calls corresponding words art recording file according to words art scheme and replies described client.
Wherein more preferably, barge module is set in described switch; Described words art recording file is in playing process, if described client is spoken, described barge module stops the broadcasting of described words art recording file at once.
Utilize real person talk skill system provided by the present invention and its implementation, significantly can reduce the labour intensity of seat person, ensure the operating efficiency that seat person continues, improve the labor productivity of call center seat person.
Accompanying drawing explanation
Fig. 1 is the overall structure schematic diagram of real person talk skill system provided by the present invention;
Fig. 2 is in real person talk skill system, the schematic flow sheet of real person talk skill implementation method;
When Fig. 3 is client incoming call, corresponding words art processing procedure sequential chart.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
The said real person talk skill of the present invention refers to record replacement text prompt with true man, and words art scheme is recorded into words art recording file by seat person in advance.When client asks a question, seat person is not constantly repeatedly read these texts after finding corresponding answer, but play-overs corresponding words art recording file.This words art recording file plays to seat person oneself simultaneously, makes seat person can grasp progress and the content of broadcasting.When client speak interrupt time, seat person can answer response very soon.This real person talk skill technical scheme can reduce the labour intensity of seat person in call center, ensures the operating efficiency that seat person continues.For realizing above-mentioned technical scheme, the invention provides corresponding real person talk skill system, can be recorded by broadcasting true man and realizing intelligence answer.Launch detailed specific description below.
As shown in Figure 1, real person talk skill system provided by the present invention comprises: client, seat end, VoIP switch, words art retrieval/playing module, words art database.Wherein can arrange barge (Barge-in) module in VoIP switch, words art retrieval/playing module can arrange sound identification module.In the present invention, client is the various outside line verbal systems with incoming call or call out function, such as mobile phone, landline telephone etc.VoIP switch is used for providing PSTN(public switched telephone network) function such as relaying access, PSTN speech channel voice and VoIP speech conversion.In VoIP switch, front end is the access of PSTN relaying, and this section is traditional telecommunication voice path, after VoIP switch, be converted to ip voice stream, makes to be ip voice stream between VoIP switch and seat end.Seat end is equipped with at least one seat person and at least one phone, and wherein phone is the phone supporting voice over ip feature, preferably uses based on hard-wired IP phone or IP softphone.Seat end and client form double-directional speech path by VoIP switch, wherein the voice messaging of the PSTN speech channel of client converts ip voice flow transmission to seat end by VoIP switch, and the ip voice that seat end is play flows through VoIP switch and converts the voice messaging of PSTN speech channel in client terminal playing.
Words art retrieval/playing module respectively with seat end with talk about art database and be bi-directionally connected.This words art retrieval/playing module has problem retrieval and recording playing function, can according to the key to the issue word of seat person's typing retrieving information in words art database, and seat end plays the words art recording file retrieved according to actual needs.Before address, in words art retrieval/playing module, can sound identification module be set, Aitalk 2.0, the InterReco 2.0 etc. of such as University of Science and Technology Xun Fei company, the automatic identification to client subject of question can be realized by this sound identification module, thus make words art retrieval/playing module directly call corresponding words art recording file according to words art scheme to reply, reduce the labour intensity of seat person further.
Words art database comprises words art search library and true man's sound bank, wherein talk about art search library for providing the search index of key to the issue word or statement,, between the search index in words art search library and the words art recording file in true man's sound bank, there are mapping relations in the words art recording file that true man's sound bank is prerecorded for storing seat end.When client asks a question, seat end first passes through words art retrieval/playing module search problem after the problem receiving client proposition; Corresponding words art recording file is play-overed to client and seat end according to the words art scheme retrieved.This words art recording file plays to seat end simultaneously, makes seat end can grasp progress and the content of broadcasting.
Below in conjunction with concrete application scenarios, real person talk skill implementation method provided by the present invention is described.As shown in Figure 2, this real person talk skill implementation method applies above-mentioned real person talk skill system, and seat person records the words art recording file of oneself in advance in words art database, and sets up corresponding mapping relations between the search index in words art search library.When the exhalation of seat end or the incoming call of acknowledged client end, between client and seat end, form double-directional speech path.When client asks a question, the problem that seat person proposes according to client, retrieves the relevant words art scheme of this problem by words art retrieval/playing module.When seat person retrieves words art scheme, click the broadcast button of words art retrieval/playing module, corresponding words art recording file is play at seat end and client simultaneously.If seat person does not retrieve problem or client when interrupting recording play session, seat end can get involved artificial treatment.
Fig. 3 shows when client is to real person talk skill system incoming call, the basic sequential of corresponding words art processing procedure.As shown in Figure 3, this words art processing procedure comprises following operating procedure:
1) client utilizes fixed phone/mobile phone to carry out incoming call to real person talk skill system;
2) VoIP switch receives incoming signal, and the voip phone to seat end sends bell signal, corresponding voip phone ring;
3) after seat end receives bell signal, off-hook is replied, and transmits response message to VoIP switch;
4) VoIP switch transmits answering call information to client after receiving response message, and now client and seat end set up double-directional speech path;
5) client sends enquirement to seat end, and the voice messaging of this enquirement transmits to VoIP switch;
6) this voice messaging passes and changes ip voice flow transmission into corresponding seat end by VoIP switch;
7) seat end is according to the voice messaging of the client enquirement received, and organizes key words to words art retrieval/playing module typing retrieving information;
8) art retrieval/playing module is talked about according to the retrieving information of seat end typing to talking about words art recording file corresponding to art database retrieval and feeding back to seat end;
In step 7) and 8) in, if arrange sound identification module in words art retrieval/playing module, then can by the automatic identification of this sound identification module realization to client subject of question, find the keyword in client subject of question, the words art scheme making words art retrieval/playing module corresponding according to this keyword is directly called corresponding words art recording file and is replied, and reduces the labour intensity of seat person further.
9) seat end is streamed to the transmission of VoIP switch with ip voice according to the words art recording file of words art retrieval/playing module feedback, and this words art recording file is play at seat end simultaneously, makes seat person can grasp progress and the content of broadcasting;
In above-mentioned steps, if words art retrieval/playing module does not retrieve relevant art recording file in words art database, seat person will directly answer with client's call.Now, seat person's OnNow one recording process.In the answer process of seat person, generate words art recording file corresponding to this key to the issue word in real time, and this words art recording file and key to the issue word are associated stored in words art database, thus words art database can be supplemented in time.
10) the ip voice traffic flow information received is converted to words art recording file to client terminal playing by VoIP switch;
11), when client sends new enquirement to seat end, step 5) ~ step 10) is repeated.
In real person talk skill system provided by the present invention, barge (Barge-in) module in VoIP switch, can be set up.In the playing process of words art recording file, if client speaks (such as proposing new problem), first barge module detects the speech energy of client, the starting point of client voice is found by end-point detection, stopping the broadcasting of existing words art recording file at once, getting involved artificial treatment by continuing in person to communicate with client or again retrieve in words art scheme.
It should be pointed out that above-described embodiment is only the process to corresponding real person talk skill when puing question to seat end acknowledged client end.Be appreciated that when seat person is to outcall, equally also can realize corresponding real person talk skill according to above-mentioned technical thought, just specifically do not repeated at this.
In sum, adopt real person talk skill system provided by the present invention and its implementation, seat person no longer repeatedly reads text prompt when processing words art problem, but play-overs corresponding words art recording file.This words art recording file plays to seat person oneself simultaneously, makes seat person can grasp progress and the content of broadcasting.When client speak interrupt time, seat person can answer response soon.This technical solution significantly can reduce the labour intensity of seat person, ensures the operating efficiency that seat person continues, and improves the labor productivity of call center seat person.
In addition, the specific embodiment of the present invention can realize with the combination of software, hardware or software and hardware.Wherein hardware components such as sound identification module, barge module etc. can utilize special logic to realize; Software section can store in memory, and by suitable instruction execution system, such as microprocessor or special designs hardware perform.Those having ordinary skill in the art will appreciate that above-mentioned method and system can use computer executable instructions and/or be included in processor control routine to realize, such as, on the programmable memory of mounting medium, such as read-only memory (firmware) or the data medium of such as optics or electrical signal carrier of such as disk, CD or DVD-ROM, provide such code.System in the present invention and assembly thereof can be realized by the hardware circuit of the programmable hardware device of the semiconductor of such as very lagre scale integrated circuit (VLSIC) or gate array, such as logic chip, transistor etc. or such as field programmable gate array, programmable logic device etc., also with the software simulating performed by various types of processor, also can be realized by the combination such as firmware of above-mentioned hardware circuit and software.
Above real person talk skill system provided by the present invention and its implementation are described in detail.For one of ordinary skill in the art, to any apparent change that it does under the prerequisite not deviating from connotation of the present invention, all by formation to infringement of patent right of the present invention, corresponding legal liabilities will be born.

Claims (8)

1. a real person talk skill system, is characterized in that comprising client, switch, seat end, words art retrieval/playing module and words art database;
Described words art retrieval/playing module is connected with described seat end, described words art database respectively, and described seat end and described client form double-directional speech path by described switch;
Described seat end, according to the voice messaging receiving client, talks about art recording file by described words art retrieval/playing module to described words art database retrieval, to described client terminal playing after retrieving required words art recording file;
Described switch comprises barge module; Described barge module detects the speech energy of client, the starting point of client voice is found by end-point detection, stop the broadcasting of existing words art recording file at once, get involved artificial treatment and continued to communicate with client or again retrieve in words art scheme by described seat end.
2. real person talk skill system as claimed in claim 1, is characterized in that:
Described switch is VoIP switch.
3. real person talk skill system as claimed in claim 1, is characterized in that:
Described words art retrieval/playing module comprises sound identification module.
4. real person talk skill system as claimed in claim 1, is characterized in that:
Described words art database comprises words art search library and true man's sound bank, there are mapping relations between the search index in described words art search library and the words art recording file in described true man's sound bank.
5. realize a method for real person talk skill, realize based on real person talk skill system according to claim 1, it is characterized in that:
When client asks a question to seat end, described seat end is by the words art retrieval/playing module words art recording file that search problem is corresponding in words art database; If words art recording file exists, then talk about art recording file directly to described in described client terminal playing, described words art recording file plays to described seat end simultaneously; If words art recording file does not exist, described seat end is directly conversed with described client and is answered a question, and starts Recording Process simultaneously and generates words art recording file in real time, and associate this words art recording file stored in described words art database with key to the issue word.
6. realize the method for real person talk skill as claimed in claim 5, it is characterized in that:
Described seat end records the words art recording file of oneself in advance in described words art database, and and sets up mapping relations between the search index in words art search library.
7. realize the method for real person talk skill as claimed in claim 5, it is characterized in that:
In described words art retrieval/playing module, sound identification module is set, by the subject of question of client described in described sound identification module identification, described words art retrieval/playing module directly calls corresponding words art recording file according to words art scheme and replies described client.
8. realize the method for real person talk skill as claimed in claim 5, it is characterized in that:
Barge module is set in described switch; Described words art recording file is in playing process, if described client is spoken, described barge module stops the broadcasting of described words art recording file at once.
CN201210344584.5A 2012-09-17 2012-09-17 For real person talk skill system and its implementation of call center Active CN102868836B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210344584.5A CN102868836B (en) 2012-09-17 2012-09-17 For real person talk skill system and its implementation of call center

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210344584.5A CN102868836B (en) 2012-09-17 2012-09-17 For real person talk skill system and its implementation of call center

Publications (2)

Publication Number Publication Date
CN102868836A CN102868836A (en) 2013-01-09
CN102868836B true CN102868836B (en) 2015-08-05

Family

ID=47447420

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210344584.5A Active CN102868836B (en) 2012-09-17 2012-09-17 For real person talk skill system and its implementation of call center

Country Status (1)

Country Link
CN (1) CN102868836B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103198828B (en) * 2013-04-03 2015-09-23 中金数据系统有限公司 The construction method of speech corpus and system
CN104168546B (en) * 2014-08-29 2018-04-10 宇龙计算机通信科技(深圳)有限公司 Automatic answering device and auto-answer method
CN105376433A (en) * 2015-09-24 2016-03-02 深圳市车音网科技有限公司 Voice automatic revisit device, system and method
CN105376432A (en) * 2015-09-24 2016-03-02 深圳市车音网科技有限公司 Voice automatic revisit device, system and method
CN107026949B (en) * 2017-02-20 2018-02-27 平安科技(深圳)有限公司 Pay a return visit the treating method and apparatus of voice messaging
CN108234785B (en) * 2018-01-16 2020-08-04 平安科技(深圳)有限公司 Telephone sales prompting method, electronic device and readable storage medium
CN108364652A (en) * 2018-01-16 2018-08-03 成都易讯呼科技有限公司 A kind of intelligent sound for artificial intelligence phone answers intersection control routine
CN108958977A (en) * 2018-06-29 2018-12-07 深圳市天聆通科技有限公司 A method of backup management being carried out to sound recordings using small table database
CN110060098A (en) * 2019-04-04 2019-07-26 秒针信息技术有限公司 The acquisition methods and device of marketing term

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101242452A (en) * 2007-02-05 2008-08-13 国际商业机器公司 Method and system for automatic generation and provision of sound document
CN101465918A (en) * 2007-12-17 2009-06-24 华为技术有限公司 Service down distributing method, service implementing method, calculation side and exchange side
CN101515970A (en) * 2008-02-22 2009-08-26 中兴通讯股份有限公司 Search engine-based customer call center system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006126966A (en) * 2004-10-26 2006-05-18 Toho Pharmaceutical Co Ltd Call center system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101242452A (en) * 2007-02-05 2008-08-13 国际商业机器公司 Method and system for automatic generation and provision of sound document
CN101465918A (en) * 2007-12-17 2009-06-24 华为技术有限公司 Service down distributing method, service implementing method, calculation side and exchange side
CN101515970A (en) * 2008-02-22 2009-08-26 中兴通讯股份有限公司 Search engine-based customer call center system

Also Published As

Publication number Publication date
CN102868836A (en) 2013-01-09

Similar Documents

Publication Publication Date Title
CN102868836B (en) For real person talk skill system and its implementation of call center
KR20210113452A (en) Handling calls on a shared speech-enabled device
US8416928B2 (en) Phone number extraction system for voice mail messages
US9160850B2 (en) Method and system for informing customer service agent of details of user's interaction with voice-based knowledge retrieval system
CN105578439A (en) Incoming call transfer intelligent answering method and system for call transfer platform
US9226159B1 (en) Telephone call challenge to block spam
US20060233335A1 (en) Request to block use of remotely selected ring tone
US10110741B1 (en) Determining and denying call completion based on detection of robocall or telemarketing call
US20090210229A1 (en) Processing Received Voice Messages
US10257350B2 (en) Playing back portions of a recorded conversation based on keywords
US20140315523A1 (en) Method using mobile-phone client side to provide voice option and text prompt and corresponding mobile-phone client side
US10637981B2 (en) Communication between users of a telephone system
JP4716930B2 (en) Call center call record management system and method
CN100563280C (en) A kind of method of source of sound being uploaded bell sound storehouse
CN103037340A (en) Calling prompting method and system
JP2015164269A (en) Automatic voice response device and automatic voice response method
US10812655B1 (en) Methods and systems for seamless outbound cold calls using virtual agents
US20210133765A1 (en) Methods and systems for socially aware virtual agents
JP4382682B2 (en) Automatic voice response device
US20210133533A1 (en) Methods and systems for seamless outbound cold calls using virtual agents
US20210134284A1 (en) Methods and systems for personalized virtual agents to learn from customers
US20210134282A1 (en) Methods and systems for personalized virtual agents to learn from customers
US20210133764A1 (en) Methods and systems for virtual agents to check caller identity via multi channels
US20210136208A1 (en) Methods and systems for virtual agent to understand and detect spammers, fraud calls, and auto dialers
US20210136195A1 (en) Methods and systems for virtual agent to understand and detect spammers, fraud calls, and auto dialers

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
C14 Grant of patent or utility model