CN101656803A - Operator position system capable of recognizing voices and voice recognition method thereof - Google Patents
Operator position system capable of recognizing voices and voice recognition method thereof Download PDFInfo
- Publication number
- CN101656803A CN101656803A CN200810141952A CN200810141952A CN101656803A CN 101656803 A CN101656803 A CN 101656803A CN 200810141952 A CN200810141952 A CN 200810141952A CN 200810141952 A CN200810141952 A CN 200810141952A CN 101656803 A CN101656803 A CN 101656803A
- Authority
- CN
- China
- Prior art keywords
- module
- speech recognition
- voice
- request
- operator position
- 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
Images
Abstract
The invention relates to an operator position system capable of recognizing voices and a voice recognition thereof. The operator position system comprises an operator position client and an application server, wherein the operator position client comprises an operator position module and a voice recognition module; and the application server comprises a manual service interface module and a WEB service module. The method comprises the following steps that: after receiving a request of starting or stopping voice recognition, the operator position module notifies a voice recognition control module; the voice recognition control module sends a corresponding command to the voice recognition module; the voice recognition module starts or stops the voice recognition according to the received command, and after the voice recognition is stopped, the recognized information is copied into a system clipboard; and the WEB service module copies contents on the clipboard to the corresponding position of the manual service interface module and then saves the contents to a database. The system and method improve the work efficiency and the service quality of telephone operators effectively, and simultaneously, improves the efficiency of a call center.
Description
Technical field
The present invention relates to communication and computer realm, specifically, relate to a kind of method of discerning the Operator Position System and the identification voice thereof of voice.
Background technology
The call center is a kind of brand-new modern service system that can make full use of existing communication means and computer technology, has caused more and more people's concern.In the world, the traffic carrying capacity growth rate of call center system is very fast.Though the domestic starting of call center system is later relatively, also become one of developing direction important in the IT industry at present, it comprises a lot of key technologies.
In worker's single current of present call center, client's complaint and fault Shen are accused and are inserted by the operator on the seat, forward the single processing interface of staying of Workflow system then to or accuse type and forward corresponding fault Shen announcement information input interface to according to client's fault Shen, after operator and client carry out talk, the operator accuses the manual corresponding text territory that is input to the interface of information to user's calling information or fault Shen again, be saved in database then, so just can have finished once to complain and stay list and fault Shen announcement to stay list.
By above flow process, we can see the staying in single process of Workflow system of call center up till now, a large amount of calling informations and fault Shen announcement information are the manual inputs of operator, this has not only increased operator's workload, thereby the easily tired operator's probability of makeing mistakes that causes of operator is increased, reduced the service quality of call center.
Through years of development, it is practical that speech recognition technology has moved towards gradually.The accuracy of identification of the continuous speech recognition system of unspecified person Chinese digital polyphone of department of electronic engineering, tsinghua university voice technology and the research and development of special chip design seminar can reach 94.8% (random length numeric string) and 96.8% (fixed length numeric string).Having under 5% the reject rate situation, system recognition rate can reach 96.9% (random length numeric string) and 98.7% (fixed length numeric string), and this is one of international best at present recognition result, and its performance is near realistic scale.At present, IBM has world-leading speech recognition technology.Many widely used now speech recognition technologies are at first proposed by IBM.The ViaVoice speech recognition software of IBM can reach more than 95% the discrimination of Chinese speech, and is easy-to-use.But yet there are no the Operator Position System that speech recognition technology is applied to the call center.
Summary of the invention
Technical problem to be solved by this invention is, a kind of Operator Position System of discerning voice is provided, and a kind of method of described Operator Position System identification voice is provided, and the present invention can significantly reduce operator's workload, improves the operating efficiency and the cost of call center.
A kind of Operator Position System of discerning voice comprises seat client computer and application server, comprises seat module and sound identification module on the described seat client computer; Comprise manual service interface module and WEB service module on the described application server,
Described seat module is used to insert voice, and notifies described speech recognition controlled module and communicate with described WEB service module when receiving the speech recognition request or stopping the speech recognition request; Comprise the speech recognition controlled module in the described seat module, this module is used to control the switch of described sound identification module;
Described sound identification module is used for the voice that insert are discerned;
Described WEB service module is used for the described manual service interface module of typing as a result with the identification of described sound identification module, and after typing finishes the information of institute's typing is saved in the database.
All has external access interface on described seat module, sound identification module, speech recognition controlled module and the WEB service module.
Described speech recognition controlled module comprises two external access interfaces, is respectively the beginning speech recognition interface and stops speech recognition interface.
Described sound identification module is an IBM ViaVoice module.
A kind of method of Operator Position System identification voice, described method comprises:
When seat module is received the speech recognition request, notify the speech recognition controlled module with described request, described speech recognition controlled module sends the beginning voice recognition commands to sound identification module, begins speech recognition after described sound identification module receives orders;
When described seat module is received when stopping the speech recognition request, stop request and notify described speech recognition controlled module described, described speech recognition controlled module sends and stops voice recognition commands to described sound identification module, after receiving orders, described sound identification module stops speech recognition, and with its information copy of discerning in system's shear plate, return the identification information of speech recognition success then and give described speech recognition controlled module;
Described speech recognition controlled module passes to the WEB service module by described seat module with described information, described WEB service module is received the described system of visit shear plate behind the identification information of speech recognition success, and the content on the described shear plate is copied to the relevant position of manual service interface module and it is saved in database.
Described seat module also is saved in database with the log information of described request when notifying its received request of described speech recognition controlled module, described log information comprises requestor, request time or requestor, dwell time.
Described seat module is notified described sound identification module by the beginning speech recognition interface of visiting described speech recognition controlled module with described speech recognition request; Notify described sound identification module by the speech recognition interface that stops of visiting described speech recognition controlled module with described stop tone identification request.
The present invention can effectively improve operator's operating efficiency and service quality, has also improved the efficient of call center simultaneously, has reduced the cost of call center.
Description of drawings
Fig. 1 is the position view of Operator Position System of the present invention in the call center;
Fig. 2 is the structured flowchart of Operator Position System of the present invention;
Fig. 3 utilizes the method for the invention to complete successfully the flow chart of a speech recognition.
Embodiment
Below in conjunction with drawings and Examples the present invention is described in further details.
Operator Position System of the present invention, the seat client computer and the application server that comprise the call center, as shown in Figure 1, the call center comprises IVR (interactive voice response) server, digital SPC exchange, CTI (Computer Telephony Integration, computer telephone integration) server, application server, database server and seat client computer, residing position is the superiors to Operator Position System of the present invention in the call center, user terminal is linked into ivr server and cti server by digital SPC exchange, cti server is distributed to each seat client computer to call request, the seat operator is by seat client access application server, call manual service processing interface and accept customer complaint request or obstacle Shen announcement etc., then above-mentioned information is saved in database server, as the Data Source of professional subsequent treatment foundation and work statistic.
Fig. 2 is the structured flowchart of Operator Position System of the present invention, Operator Position System of the present invention comprises seat client computer and application server, comprise seat module and sound identification module on the described seat client computer, described seat module is used for voice and inserts, and when receiving the speech recognition request or stopping the speech recognition request notice speech recognition controlled module and communicate with the WEB service module, also include the speech recognition controlled module in this module, described speech recognition controlled module is used to control the switch of sound identification module; Sound identification module is used for the voice that insert are discerned, and in the present embodiment, sound identification module adopts IBM ViaVoice module; Comprise manual service interface module and WEB service module on the application server of Operator Position System of the present invention, the WEB service module is used for the described manual service interface module of typing as a result with sound identification module identification, and after typing finishes the information of institute's typing is saved in the database.
All has external access interface on described seat module, sound identification module, speech recognition controlled module and the WEB service module, and described speech recognition controlled module comprises two external access interfaces, is respectively the beginning speech recognition interface and stops speech recognition interface.
Fig. 3 utilizes the method for the invention to complete successfully the flow chart of a speech recognition, specifically comprises the steps:
1, the service needed speech recognition accepted of seat triggers seat module and initiates the speech recognition request;
2, the beginning speech recognition interface of seat module access voice identification control module is notified the speech recognition controlled module with described request, and log information recordings such as the requestor of described request, request times to database;
3, the speech recognition controlled module sends the beginning voice recognition commands to IBM ViaVoice module, and the IBMViaVoice module begins speech recognition;
4, during described service ending, trigger seat module and initiate to stop the speech recognition request;
5, the speech recognition interface that stops of seat module access voice identification control module stops request notice speech recognition controlled module with described, and log information recordings such as the described requestor who stops to ask, dwell times to database;
6, the speech recognition controlled module sends and stops voice recognition commands to IBM ViaVoice module, the IBMViaVoice module stops speech recognition, and the text copy that has identified in system's shear plate, return the identification information that sign voice are identified as merit then and give the speech recognition controlled module;
In other embodiments, if this step speech recognition failure, then sound identification module can return the identification information of a sign voice recognition failures to the speech recognition controlled module;
7, the speech recognition controlled module is received the identification information that IBM ViaVoice module is returned, and this identification information is returned to seat module;
8, seat is after receiving identification information, send it to the WEB service module, the WEB service module copies content identified in the corresponding text control of manual service interface module to automatically by interface accessing system shear plate, and the content in the described text control can be edited.
In other embodiments, if whether success is unknown for the speech recognition of described identification information sign, then this moment, seat module can be after receiving the identification information that returns, judge whether it discerns success, if discern successfully, then notify after the notice that WEB service module speech recognition success, WEB service module receive the speech recognition success by interface accessing system shear plate, automatically content identified is copied in certain text control of manual service interface module; Otherwise notice WEB service module speech recognition failure, the WEB service module is left intact.
The operation that described information with sound identification module identification copies to the corresponding text control of manual service interface module from system's shear plate also can be by manually finishing, be after the seat module suggestion voice is discerned successfully, traffic moves on to focus on the corresponding text control, clicks the Ctrl+V shortcut content in system's shear plate is copied on the manual service interface module.
In the practical application,, be saved in then in text or the Word file and send to the user again when some contents that need report the operator when sending to the client, can adopt the present invention to discern operator's voice with the form (mail, note) of text; The present invention also can be applicable to operator's examination aspect, and the talk that is about between operator and the client identifies, and saves as text respectively, as the foundation of examination operator work.
More than comparatively detailed at the description of preferred embodiment; but can not therefore think limitation of the present invention; all and disclosed principle is similarly implemented, and all in protection scope of the present invention, protection scope of the present invention should be as the criterion with claims.
Claims (7)
1, a kind of Operator Position System of discerning voice is characterized in that, comprises seat client computer and application server, comprises seat module and sound identification module on the described seat client computer; Comprise manual service interface module and WEB service module on the described application server,
Described seat module is used to insert voice, and notifies described speech recognition controlled module and communicate with described WEB service module when receiving the speech recognition request or stopping the speech recognition request; Comprise the speech recognition controlled module in the described seat module, this module is used to control the switch of described sound identification module;
Described sound identification module is used for the voice that insert are discerned;
Described WEB service module is used for the described manual service interface module of typing as a result with the identification of described sound identification module, and after typing finishes the information of institute's typing is saved in the database.
2, the Operator Position System of discerning voice as claimed in claim 1 is characterized in that, all has external access interface on described seat module, sound identification module, speech recognition controlled module and the WEB service module.
3, the Operator Position System of discerning voice as claimed in claim 2 is characterized in that, described speech recognition controlled module comprises two external access interfaces, is respectively the beginning speech recognition interface and stops speech recognition interface.
4, the Operator Position System of discerning voice as claimed in claim 1 or 2 is characterized in that, described sound identification module is an IBM ViaVoice module.
5, a kind of method of Operator Position System identification voice is characterized in that described method comprises:
When seat module is received the speech recognition request, notify the speech recognition controlled module with described request, described speech recognition controlled module sends the beginning voice recognition commands to sound identification module, begins speech recognition after described sound identification module receives orders;
When described seat module is received when stopping the speech recognition request, stop request and notify described speech recognition controlled module described, described speech recognition controlled module sends and stops voice recognition commands to described sound identification module, after receiving orders, described sound identification module stops speech recognition, and with its information copy of discerning in system's shear plate, return the identification information of speech recognition success then and give described speech recognition controlled module;
Described speech recognition controlled module passes to the WEB service module by described seat module with described information, described WEB service module is received the described system of visit shear plate behind the identification information of speech recognition success, and the content on the described shear plate is copied to the relevant position of manual service interface module and it is saved in database.
6, the method for Operator Position System identification voice as claimed in claim 5, it is characterized in that, described seat module also is saved in database with the log information of described request when notifying its received request of described speech recognition controlled module, described log information comprises requestor, request time or requestor, dwell time.
7, the method for Operator Position System identification voice as claimed in claim 5 is characterized in that described seat module is notified described sound identification module by the beginning speech recognition interface of visiting described speech recognition controlled module with described speech recognition request; Notify described sound identification module by the speech recognition interface that stops of visiting described speech recognition controlled module with described stop tone identification request.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810141952A CN101656803A (en) | 2008-08-20 | 2008-08-20 | Operator position system capable of recognizing voices and voice recognition method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810141952A CN101656803A (en) | 2008-08-20 | 2008-08-20 | Operator position system capable of recognizing voices and voice recognition method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101656803A true CN101656803A (en) | 2010-02-24 |
Family
ID=41710879
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810141952A Pending CN101656803A (en) | 2008-08-20 | 2008-08-20 | Operator position system capable of recognizing voices and voice recognition method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101656803A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299967A (en) * | 2011-09-08 | 2011-12-28 | 中兴通讯股份有限公司 | Mobile position system, gateway, mobile terminal and method for realizing mobile position |
| WO2013174092A1 (en) * | 2012-05-23 | 2013-11-28 | 华为技术有限公司 | Speech recognition based query method and apparatus |
| CN103810211A (en) * | 2012-11-15 | 2014-05-21 | 殷程 | Intelligent voice knowledge base |
| CN106170829A (en) * | 2014-02-24 | 2016-11-30 | 霍尼韦尔国际公司 | Sound for industrial operation person's control station is strengthened |
-
2008
- 2008-08-20 CN CN200810141952A patent/CN101656803A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102299967A (en) * | 2011-09-08 | 2011-12-28 | 中兴通讯股份有限公司 | Mobile position system, gateway, mobile terminal and method for realizing mobile position |
| WO2013174092A1 (en) * | 2012-05-23 | 2013-11-28 | 华为技术有限公司 | Speech recognition based query method and apparatus |
| CN103810211A (en) * | 2012-11-15 | 2014-05-21 | 殷程 | Intelligent voice knowledge base |
| CN106170829A (en) * | 2014-02-24 | 2016-11-30 | 霍尼韦尔国际公司 | Sound for industrial operation person's control station is strengthened |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105530387B (en) | The call processing method of IVR system | |
| CN110891124B (en) | System for artificial intelligence pick-up call | |
| US7254384B2 (en) | Multi-modal messaging | |
| US7783028B2 (en) | System and method of using speech recognition at call centers to improve their efficiency and customer satisfaction | |
| CN103714813A (en) | Phrase spotting systems and methods | |
| JP2000013510A (en) | Automatic calling and data transfer processing system and method for providing automatic calling or message data processing | |
| CN102572134A (en) | Work order processing method, work order building system and work order processing system | |
| WO2002051114A1 (en) | Service request processing performed by artificial intelligence systems in conjunction with human intervention | |
| AU2005200320A1 (en) | Recognition results postprocessor for use in voice recognition systems | |
| CN111080926B (en) | Auxiliary interaction method and device for self-service equipment | |
| CN111583931A (en) | Service data processing method and device | |
| CN109246310A (en) | It is a kind of that auxiliary system is answered based on intelligent sound technology | |
| WO2013174092A1 (en) | Speech recognition based query method and apparatus | |
| CN101656803A (en) | Operator position system capable of recognizing voices and voice recognition method thereof | |
| CN110782341A (en) | Business collection method, device, equipment and medium | |
| US20050069122A1 (en) | System and method for operator assisted automated call handling | |
| CN111831875A (en) | Data processing method, device, equipment and storage medium | |
| KR20170073417A (en) | System for response correspond to mobile message | |
| CN110705926A (en) | Method, device and system for acquiring logistics object distribution information | |
| CN108418979B (en) | Telephone traffic continuation prompting method and device, computer equipment and storage medium | |
| CN113542509B (en) | Emergency processing method, device, storage medium and equipment | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| CN113301214B (en) | Intelligent work order system | |
| US8447027B2 (en) | System and method for language variation guided operator selection | |
| CN112133306B (en) | Response method and device based on express delivery user and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20100224 |