CN109040485B - High-speed service hotline intelligent panoramic voice navigation system based on natural language processing - Google Patents
High-speed service hotline intelligent panoramic voice navigation system based on natural language processing Download PDFInfo
- Publication number
- CN109040485B CN109040485B CN201811005457.6A CN201811005457A CN109040485B CN 109040485 B CN109040485 B CN 109040485B CN 201811005457 A CN201811005457 A CN 201811005457A CN 109040485 B CN109040485 B CN 109040485B
- Authority
- CN
- China
- Prior art keywords
- module
- error
- navigation
- service
- natural language
- 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
Links
Images
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
- H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The embodiment of the invention provides a high-speed service hotline intelligent panoramic voice navigation system based on natural language processing, which comprises a voice recognition module, a semantic understanding module, an IVR module, an operation log module, a TTS module, an intelligent interruption module, an error processing module, a global command module, a panoramic navigation module, a road sign guiding module and a navigation grammar file. The invention adopts advanced natural language processing technology, so that a user can interact with the system by using natural language.
Description
Technical Field
The invention relates to the technical field of intelligent navigation, in particular to a high-speed service hotline intelligent panoramic voice navigation system based on natural language processing.
Background
The high-speed customer service hotline is generally based on Computer and communication technology, and applies traditional call center technology such as CTI (Computer telephony integration), IVR (Interactive Voice Response) and the like to provide information consultation and query service for customers. The high-speed customer service hotline adopts a service mode of combining manual customer service and IVR voice navigation at present.
With the increasing number of service items in the high-speed customer service IVR, the inherent disadvantages and difficulties become more and more prominent, most notably, the menu hierarchy is too many, the key input is troublesome, which affects the use of the voice service by the customer, and even some customers can directly abandon the use of the voice service.
With the continuous expansion of high-speed customer service services, the newly added services can only be placed under deep nodes by adopting a traditional key mode. Therefore, most users need to interact for many times to reach the nodes, and when the users cannot acquire the services which need to be inquired, the users can directly switch to manual service, so that the pressure of the manual service is greatly increased.
Disclosure of Invention
The embodiment of the invention provides a high-speed service hotline intelligent panoramic voice navigation system based on natural language processing, which is used for solving the problems of deep menu hierarchy, limited service bearing and long interaction time consumption of high-speed customer service navigation.
In order to solve the technical problem, the embodiment of the invention discloses the following technical scheme:
the invention provides a high-speed service hotline intelligent panoramic voice navigation system based on natural language processing, which comprises a voice recognition module, a semantic understanding module, an IVR module, an operation log module and a TTS module, wherein the system is deployed in a server; and the combination of (a) and (b),
the error processing module is used for carrying out corresponding processing according to the error content when the system identifies that an error occurs; and the combination of (a) and (b),
the global command module is used for transferring to the corresponding business module according to the recognized command words and the navigation grammar file under any business node; and the combination of (a) and (b),
the panoramic navigation module is used for jumping to a corresponding service module according to the received voice prompt information and the navigation grammar file under any service state; and the combination of (a) and (b),
the road sign guiding module is used for giving a road sign prompt tone after receiving the requirements of the user and determining the current business module and the business state; and the combination of (a) and (b),
a navigation grammar file containing parameters and a path of the specified resource; the path of the specified resource comprises an ID of a semantic resource and an ID of a transliteration resource; the semantic resources comprise resources for semantic understanding of characters, and the transcription resources comprise resource files for converting voice into characters.
In a first possible implementation manner, the error processing module includes a speech recognition error processing module for providing an error prompt when speech recognition has an error, and connecting to a correct service module; and the combination of (a) and (b),
and the interface calling error processing module is used for providing a corresponding voice prompt according to a preset service flow and carrying out skipping of a subsequent flow when the interface calling fails in the process of calling the system interface after the voice recognition is successful.
In a second possible implementation, the error type of speech recognition includes rejection, the received natural language is not covered by semantic resources in the navigation grammar file, or the speech recognition module cannot accurately recognize the natural language due to background noise; and the combination of (a) and (b),
overtime, the speech recognition module does not receive the natural language signal within the specified time; and the combination of (a) and (b),
the key is wrong, and the system receives wrong key input.
In a third possible implementation manner, the error processing module further includes three dialog modules set according to different service modules, types of errors, and maximum allowable error times:
the dialog module one comprises the maximum allowable error frequency of one time, when the first error occurs, the error type is not distinguished, and the next service module is entered according to the preset service flow;
the second dialogue module comprises two maximum allowable error times, and when the first error occurs, corresponding error recovery is carried out according to different error types; when a second error occurs, the type of the error is not distinguished, and a navigation main menu is entered from the current service module according to a preset service flow;
and the third dialog module comprises a third maximum allowable error frequency, performs corresponding error recovery according to different error types when a first error or a second error occurs, does not distinguish the error types when a third error occurs, and enters a navigation main menu from the current service module according to a preset service flow.
In a fourth possible implementation manner, the error recovery includes giving corresponding warning tones according to different error types.
In a fifth possible implementation manner, the interface call error processing module performs subsequent flow skipping according to a preset service flow, where the subsequent flow skipping includes:
skipping from the current service module to a navigation main menu module;
skipping from the current service module to the manual module;
and skipping to an IVR key menu from the current service module.
In a sixth possible implementation manner, the command words include manual, help, return, main menu, and re-listening.
In a seventh possible implementation manner, the system further includes a sound effect module, which is different from the system prompt sound, and is used for prompting the specific sound effect after interaction, including a sound effect of successful operation, a sound effect of failed operation, and a sound effect of a brand.
In an eighth possible implementation manner, the brand sound effect is played after entering the autonomous voice navigation system.
According to the technical scheme, the intelligent voice interaction system is improved for the customer service hotline system. The system adopts natural language processing technology, comprising: speech recognition, speech synthesis, natural language understanding techniques enable users to interact with the system using natural language.
The embodiment of the invention adopts the intelligent interruption module, so that a user can speak own requirements while playing the prompt tone without waiting for the completion of the playing of the prompt tone, can directly reach the interactive node which the user wants to need, does not need the help of manual service, avoids the problem of deep hierarchy of the needed node and saves time.
The error processing module of the embodiment of the invention can perform corresponding error processing when the system has errors. The global command module can realize the specific function of any command word in any link capable of supporting recognition, thereby improving the efficiency.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art of the present invention, the drawings used in the description of the embodiments or prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a high-speed service hotline intelligent panoramic voice navigation system based on natural language processing.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to interact with the system quickly, the embodiment of the invention provides a high-speed service hotline intelligent panoramic voice navigation system based on natural language processing.
As shown in fig. 1, the system includes a voice recognition module, a semantic understanding module, an IVR module, an operation log module and a TTS module, wherein the IVR module submits the acquired natural language to the voice recognition module for recognition, the voice recognition module sends the recognition result to the semantic understanding module, the semantic understanding module sends the recognized result to the IVR module or the TTS module, and the IVR module or the TTS module sends the query result to the client in different forms; the system also comprises an intelligent interruption module which is used for interrupting the interactive business process according to the received natural language information analyzed by the semantic understanding module at any node in the navigation interactive process; and an error processing module for performing corresponding processing according to the error content when the system identifies that an error occurs; and a global command module for transferring to the corresponding service module according to the recognized command words and the navigation grammar file under any service node; and a panoramic navigation module for skipping to the corresponding service module according to the received voice prompt information and the navigation grammar file under any service state; and a road sign guiding module for giving road sign prompt tone after receiving the user's demand, and defining the current service module and service state; and, a navigation grammar file containing parameters, a path specifying the resource; the path of the specified resource comprises an ID of a semantic resource and an ID of a transliteration resource; the semantic resources comprise resources for semantic understanding of characters, and the transcription resources comprise resource files for converting voice into characters.
When the intelligent interruption is carried out, the system monitors and receives natural voice at any time, when a natural voice signal is received, the voice recognition module and the semantic understanding module recognize and analyze the natural voice, interrupt the interactive business flow according to the analyzed semantic and turn to the needed business flow.
The command words of the global command include: manual operation, help, return, main menu and re-listening. The main role of the command word is shown in the following table:
| global commands | The main effects are |
| Help (help) | Providing a usage guide for a current dialog state |
| Return to | Return toUpper layer (Main menu not supporting) |
| Main menu | Jump to main menu (main menu not supporting) |
| Transferred to manual work | Jump to manual service |
The global command module is limited to fixed menu commands, such as the above 5 commands. Panoramic navigation is only directed to commands of a business layer, such as: "inquire the toll from jiao zhou to the south of china".
The error processing module comprises a voice recognition error processing module which is used for providing error prompt when the voice recognition has errors and is connected to the correct service module; and the interface calling error processing module is used for providing a corresponding voice prompt according to a preset service flow and carrying out skipping of a subsequent flow when the interface calling fails in the process of calling the system interface after the voice recognition is successful.
The error of the voice recognition comprises rejection, the received natural language is not covered by semantic resources in the navigation grammar file, or the voice recognition module can not accurately recognize the natural language due to background noise; and, overtime, the speech recognition module does not receive the natural language signal within the specified time; and, a key press error, the system receiving the wrong key press input.
The error processing module also comprises three dialogue modules which are arranged according to different service modules, error types and maximum allowable error times:
the first dialog module comprises a dialog module, wherein the maximum allowable error frequency is one time, when a first error occurs, the type of the error is not distinguished, and the dialog module enters the next service module according to a preset service flow;
the second dialogue module comprises a second dialogue module and a second dialogue module, wherein the maximum allowable error frequency is two times, and when a first error occurs, corresponding error recovery is carried out according to different error types; when a second error occurs, the type of the error is not distinguished, and a navigation main menu is entered from the current service module according to a preset service flow;
and the third dialog module comprises a third dialog module, wherein the maximum allowable error frequency is three times, when a first error or a second error occurs, corresponding error recovery is carried out according to different error types, when a third error occurs, the error types are not distinguished, and a navigation main menu is entered from the current service module according to a preset service flow.
The error recovery comprises giving corresponding prompt tones according to different error types. Such as: when the recognition rejection error occurs, the system prompts 'the system cannot recognize the voice and please record the voice again'; when the timeout error occurs, the system prompts 'please record voice'; when a key press error occurs, the system prompts the user to input the correct key press.
The interface calls the subsequent flow jump that the error processing module carries on according to the business flow preserved to include:
skipping from the current service module to a navigation main menu module;
skipping from the current service module to the manual module;
and skipping to an IVR key menu from the current service module.
The system also comprises a sound effect module which is different from the system prompt sound and used for prompting the specific sound effect after interaction, wherein the specific sound effect comprises a sound effect of successful operation, a sound effect of failed operation and a sound effect of a brand.
The operation success sound effect is used for the prompt tone played after the system service interaction is successful, and the operation failure sound effect is used for the prompt tone after the system service interaction is failed. And the brand sound effect is used for playing after entering the autonomous voice navigation system.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (5)
1. A high-speed service hotline intelligent panoramic voice navigation system based on natural language processing comprises a voice recognition module, a semantic understanding module, an IVR module, an operation log module and a TTS module, and is characterized in that the system is deployed in a server and also comprises an intelligent interruption module, wherein the intelligent interruption module is used for interrupting an interactive business process at any node in a navigation interaction process according to received natural language information analyzed by the semantic understanding module; and the combination of (a) and (b),
the error processing module is used for carrying out corresponding processing according to the error content when the system identifies that an error occurs; and the combination of (a) and (b),
the global command module is used for transferring to the corresponding business module according to the recognized command words and the navigation grammar file under any business node; and the combination of (a) and (b),
the panoramic navigation module is used for jumping to a corresponding service module according to the received voice prompt information and the navigation grammar file under any service state; and the combination of (a) and (b),
the road sign guiding module is used for giving a road sign prompt tone after receiving the requirements of the user and determining the current business module and the business state; and the combination of (a) and (b),
a navigation grammar file containing parameters and a path of the specified resource; the path of the specified resource comprises an ID of a semantic resource and an ID of a transliteration resource; the semantic resources comprise resources for semantic understanding of characters, and the transcription resources comprise resource files for converting voice into characters; the error processing module comprises a voice recognition error processing module which is used for providing error prompt when the voice recognition has errors and is connected to the correct service module; and the combination of (a) and (b),
the interface calling error processing module is used for providing a corresponding voice prompt according to a preset service flow and carrying out skipping of a subsequent flow when the interface calling fails in the process of calling the system interface after the voice recognition is successful; the error type of the voice recognition comprises rejection, the received natural language is not covered by semantic resources in the navigation grammar file, or the voice recognition module can not accurately recognize the natural language due to background noise; and the combination of (a) and (b),
overtime, the speech recognition module does not receive the natural language signal within the specified time; and the combination of (a) and (b),
the key is wrong, and the system receives wrong key input;
the error processing module also comprises three dialogue modules which are arranged according to different service modules, error types and maximum allowed error times:
the first dialog module comprises a dialog module, wherein the maximum allowable error frequency is one time, when a first error occurs, the type of the error is not distinguished, and the dialog module enters the next service module according to a preset service flow;
the second dialogue module comprises a second dialogue module and a second dialogue module, wherein the maximum allowable error frequency is two times, and when a first error occurs, corresponding error recovery is carried out according to different error types; when a second error occurs, the type of the error is not distinguished, and a navigation main menu is entered from the current service module according to a preset service flow;
the third dialog module comprises a third dialog module, wherein the maximum allowable error frequency is three times, when a first error or a second error occurs, corresponding error recovery is carried out according to different error types, when a third error occurs, the error types are not distinguished, and a navigation main menu is entered from the current service module according to a preset service flow;
the interface call error processing module performs subsequent flow skipping according to a preset service flow, and the subsequent flow skipping comprises the following steps:
skipping from the current service module to a navigation main menu module;
skipping from the current service module to the manual module;
and skipping to an IVR key menu from the current service module.
2. The system of claim 1, wherein the error recovery comprises presenting corresponding alert tones based on different error types.
3. The system of claim 1, wherein said command words include manual, help, return, main menu, and re-listen.
4. The system of claim 1, further comprising a sound effect module, distinct from the system alert sound, for interactive specific sound effect cues including successful operation sound effect, failed operation sound effect and brand sound effect.
5. The system of claim 4, wherein the brand sound effect is played after entering the autonomous voice navigation system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811005457.6A CN109040485B (en) | 2018-08-30 | 2018-08-30 | High-speed service hotline intelligent panoramic voice navigation system based on natural language processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811005457.6A CN109040485B (en) | 2018-08-30 | 2018-08-30 | High-speed service hotline intelligent panoramic voice navigation system based on natural language processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040485A CN109040485A (en) | 2018-12-18 |
| CN109040485B true CN109040485B (en) | 2020-08-28 |
Family
ID=64626367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811005457.6A Active CN109040485B (en) | 2018-08-30 | 2018-08-30 | High-speed service hotline intelligent panoramic voice navigation system based on natural language processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040485B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3924962A1 (en) * | 2019-05-06 | 2021-12-22 | Google LLC | Automated calling system |
| CN110275948A (en) * | 2019-05-30 | 2019-09-24 | 平安科技（深圳）有限公司 | Free jump method, device and the medium of Self-Service |
| CN110392165A (en) * | 2019-06-28 | 2019-10-29 | 贵阳朗玛信息技术股份有限公司 | A kind of method and device of the pressure test of IVR system |
| CN112333341A (en) * | 2020-10-27 | 2021-02-05 | 北京聚通达科技股份有限公司 | Intelligent voice robot system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512483A (en) * | 2002-12-27 | 2004-07-14 | 联想(北京)有限公司 | Method for realizing state conversion |
| CN102300007A (en) * | 2010-06-23 | 2011-12-28 | 上海博路信息技术有限公司 | Flattening menu system for call center based on voice identification |
| CN104079729A (en) * | 2013-03-29 | 2014-10-01 | 上海城际互通通信有限公司 | IVR information query method |
| CN104486516A (en) * | 2014-11-13 | 2015-04-01 | 国网浙江省电力公司电力科学研究院 | Robot voice service method of 95598 large telephone traffic-based IVR (Interactive Voice Response) intelligent system |
| CN105469797A (en) * | 2015-12-31 | 2016-04-06 | 广东翼卡车联网服务有限公司 | Method and system for controlling switching-over from intelligent voice identification to manual services |
| US9686408B2 (en) * | 2007-01-03 | 2017-06-20 | Foncloud, Inc. | System and method for indexing automated telephone systems |
-
2018
- 2018-08-30 CN CN201811005457.6A patent/CN109040485B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512483A (en) * | 2002-12-27 | 2004-07-14 | 联想(北京)有限公司 | Method for realizing state conversion |
| US9686408B2 (en) * | 2007-01-03 | 2017-06-20 | Foncloud, Inc. | System and method for indexing automated telephone systems |
| CN102300007A (en) * | 2010-06-23 | 2011-12-28 | 上海博路信息技术有限公司 | Flattening menu system for call center based on voice identification |
| CN104079729A (en) * | 2013-03-29 | 2014-10-01 | 上海城际互通通信有限公司 | IVR information query method |
| CN104486516A (en) * | 2014-11-13 | 2015-04-01 | 国网浙江省电力公司电力科学研究院 | Robot voice service method of 95598 large telephone traffic-based IVR (Interactive Voice Response) intelligent system |
| CN105469797A (en) * | 2015-12-31 | 2016-04-06 | 广东翼卡车联网服务有限公司 | Method and system for controlling switching-over from intelligent voice identification to manual services |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040485A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109040485B (en) | High-speed service hotline intelligent panoramic voice navigation system based on natural language processing | |
| US7487095B2 (en) | Method and apparatus for managing user conversations | |
| US8000973B2 (en) | Management of conversations | |
| US7907705B1 (en) | Speech to text for assisted form completion | |
| US7783475B2 (en) | Menu-based, speech actuated system with speak-ahead capability | |
| US6882973B1 (en) | Speech recognition system with barge-in capability | |
| US7783028B2 (en) | System and method of using speech recognition at call centers to improve their efficiency and customer satisfaction | |
| US20100151889A1 (en) | Automated Text-Based Messaging Interaction Using Natural Language Understanding Technologies | |
| US10382624B2 (en) | Bridge for non-voice communications user interface to voice-enabled interactive voice response system | |
| US7318029B2 (en) | Method and apparatus for a interactive voice response system | |
| CA2537741A1 (en) | Dynamic video generation in interactive voice response systems | |
| CN101847406B (en) | Speech recognition query method and system | |
| CN100587808C (en) | Method and apparatus for voice message editing | |
| US20060069563A1 (en) | Constrained mixed-initiative in a voice-activated command system | |
| US20050069122A1 (en) | System and method for operator assisted automated call handling | |
| WO2015166391A1 (en) | Voice call diversion to alternate communication method | |
| CN111508477A (en) | Voice broadcasting method, device, equipment and storage device | |
| CN111094924A (en) | Data processing apparatus and method for performing voice-based human-machine interaction | |
| US8949134B2 (en) | Method and apparatus for recording/replaying application execution with recorded voice recognition utterances | |
| WO2015188454A1 (en) | Method and device for quickly accessing ivr menu | |
| US20080086690A1 (en) | Method and System for Hybrid Call Handling | |
| CN111563182A (en) | Voice conference record storage processing method and device | |
| US7451086B2 (en) | Method and apparatus for voice recognition | |
| US6662157B1 (en) | Speech recognition system for database access through the use of data domain overloading of grammars | |
| US10824520B2 (en) | Restoring automated assistant sessions |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |