CN110830661A - Automatic dial testing method for intelligent voice customer service - Google Patents
Automatic dial testing method for intelligent voice customer service Download PDFInfo
- Publication number
- CN110830661A CN110830661A CN201911095755.3A CN201911095755A CN110830661A CN 110830661 A CN110830661 A CN 110830661A CN 201911095755 A CN201911095755 A CN 201911095755A CN 110830661 A CN110830661 A CN 110830661A
- Authority
- CN
- China
- Prior art keywords
- dial
- dial testing
- testing
- voice
- alarm
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/26—Arrangements for supervision, monitoring or testing with means for applying test signals or for measuring
- H04M3/28—Automatic routine testing ; Fault testing; Installation testing; Test methods, test equipment or test arrangements therefor
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2218—Call detail recording
-
- 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
Abstract
The invention discloses an automatic dial testing method for intelligent voice customer service, and relates to the technical field of voice communication testing. The invention comprises the following steps: step S1, creating an automatic dial testing task: the business process editor pre-compiles a dial testing business process and dial testing parameters; step S2, triggering a task to be dial and tested: capturing voice audio stream in real time, and performing audio real-time transcription by the server; step S3, semantic recognition processing and analysis: transferring the transcription result to an intention processing module for semantic recognition and analysis of intention, and recognizing a dial testing action; step S4, voice recording transcoding: transcoding the PCM file generated by the whole-course recording to generate a WAV file code; step S5, logging: and recording the voice dial testing data and the dial testing log information. According to the invention, through constructing the automatic dial testing basic module, setting flexible monitoring mode and flow configuration, the basic function of dial testing is upgraded and optimized, uninterrupted detection can be realized, the manual dial testing efficiency is improved, problems can be found in time, and active warning is realized.
Description
Technical Field
The invention belongs to the technical field of voice communication testing, and particularly relates to an automatic dial testing method for intelligent voice customer service.
Background
With the advancement of voice technology in the modern society, voice navigation technology has become the mainstream configuration of the customer service center of the operator. The traditional means is a mode of manual dial testing and text interactive testing, so that the manual testing is time-consuming and labor-consuming, and the efficiency is low; flow faults cannot be found in time; text testing cannot simulate a real environment; and the service flow coverage is narrow.
How to effectively detect the quality of an intelligent voice flow becomes a problem which puzzles operators, and an automatic dial testing method which covers the whole service flow needs to be researched urgently to replace manual dial testing and actively monitor the voice domain operation quality and the service accuracy of an intelligent customer service system. The automatic dialing and testing potential is fully developed, a voice domain efficient operation and maintenance mechanism is established, service operators are supported to monitor, test and optimize key high-frequency processes, and the applicability and stability of the intelligent customer service system are improved.
Disclosure of Invention
The invention aims to provide an automatic dial testing method for intelligent voice customer service, which upgrades and optimizes the basic functions of dial testing by constructing an automatic dial testing basic module and setting a flexible monitoring mode and flow configuration, and solves the problems that the existing manual testing efficiency is low and faults cannot be found in time.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to an automatic dial testing method for intelligent voice customer service, which comprises the following steps:
step S1 creates an automatic dial testing task: the business process editor pre-compiles a dial testing business process and dial testing parameters, and creates and starts a dial testing task;
step S2 triggers the task to be dial: capturing voice audio stream in real time through an MRCP module of a GCPBX dial-test platform, and transmitting the voice audio stream to an MRCP server side through an MRCP protocol for audio real-time transcription;
step S3 semantic recognition processing analysis: transferring the transcription result to an intention processing module for semantic recognition processing and intention analysis, and recognizing further dial testing actions;
step S4 voice recording transcoding: transcoding the PCM file generated by the whole-course recording to generate a WAV file code conforming to the interface calling;
step S5 logging: and recording the process data of the voice dial test and the dial test log information and providing an interface service operation platform for calling, analyzing and processing.
Preferably, in step S1, the preset dial-up test parameters include dial-up test time, dial-up test procedure, alarm text or voice, alarm threshold setting, and alarm notification level.
Preferably, in step S3, the semantic recognition processing module includes inputting a text after speech recognition, corpus collection, corpus training, corpus cleaning, format conversion, word segmentation or data set segmentation, model training, model evaluation or verification, model storage and intention recognition, and finally outputting a recognized intention result.
Preferably, in the dial testing process, when a fault or an error occurs in any process step and an alarm mechanism is triggered, the alarm notification module notifies the operation and maintenance personnel in a set alarm mode according to an alarm strategy and alarm information configured by a user.
Preferably, after the dial testing is completed, the detailed recording, the data in the dial testing process and the dial testing log of the whole dial testing process are stored, and the information recording level is set, so that a data analysis and support basis is provided for other business operation systems.
The invention has the following beneficial effects:
(1) according to the invention, by constructing an automatic dial testing basic module, setting a flexible monitoring mode and flow configuration, the basic function of dial testing is upgraded and optimized, uninterrupted detection can be realized, the manual dial testing efficiency is improved, and fault information can be solved in time;
(2) by covering the IVR key and the whole service process of the intelligent client, the invention can repeatedly dial and test important service processes, thereby ensuring the normal operation of the intelligent voice customer service platform;
(3) according to the invention, by setting the monitoring index threshold value to be compared with the actual dial-up test condition, and according to the alarm level, the telephone capable of realizing serious alarm informs related operation and maintenance personnel, and automatically sends the dial-up test alarm condition to the operation and maintenance personnel for processing in time, so that the whole operation monitoring closed-loop management is realized;
(4) the invention can generate detailed data for the operation analysis of the service system in the dial testing process, generate various types of log information and dial testing process data in the dial testing process, and set the information recording level by a user to provide data support for other operation systems.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of the steps of an automatic dial-up test method for intelligent voice customer service according to the present invention;
FIG. 2 is a diagram of the semantic recognition processing and analysis steps performed by the intent processing module of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
Referring to fig. 1, the present invention is an automatic dial testing method for intelligent voice customer service, including the following steps:
step S1 creates an automatic dial testing task: the business process editor pre-compiles a dial testing business process and dial testing parameters, and creates and starts a dial testing task;
step S2 triggers the task to be dial: capturing voice audio stream in real time through an MRCP module of a GCPBX dial-test platform, and transmitting the voice audio stream to an MRCP server side through an MRCP protocol for audio real-time transcription;
step S3 semantic recognition processing analysis: the transcription result is sent to an intention processing module for semantic recognition processing and intention analysis, and further dial testing actions are recognized, so that the purpose of service dial testing is achieved;
step S4 voice recording transcoding: transcoding the PCM file generated by the whole-course recording to generate a WAV file code conforming to the interface calling;
step S5 logging: and recording the process data of the voice dial test and the dial test log information and providing an interface service operation platform for calling, analyzing and processing.
In step S1, the preset dial-up test parameters include dial-up test time, dial-up test flow, alarm text or voice, alarm threshold setting, alarm notification level, and the like; through a customized dial testing process and strategy, uninterrupted automatic detection can be realized for 7 × 24 hours; the repeated dial testing of the whole service flow (the whole service flow covering IVR keys and intelligent voice customer service) can be realized by defining a complex dial testing flow, the problem can be found only by the feedback after the use of a client or analyzing the use data of a background in the past, and the file method can simulate manual dial testing of the 10000 platform every 24 hours, so that the problem that the fault cannot be found timely in the past is solved.
Referring to fig. 2, in step S3, the semantic recognition processing module includes inputting a text after speech recognition, corpus collection, corpus training, corpus cleansing, format conversion, word segmentation or data set segmentation, model training, model evaluation or verification, model storage and intent recognition, and finally outputting a recognized intent result, and the intent recognition processing is based on a client portrait model (an effective client portrait model is formed by client data collection, cleansing analysis and data modeling), and can be classified in combination with a modified fastText model structure, and the client intent can be subdivided into a "business query class" and a "business transaction class", which is characterized in that it can realize accurate recognition of intent in a shorter time.
In the dial testing process, when a fault or an error occurs in any process step and an alarm mechanism is triggered, the alarm notification module notifies operation and maintenance personnel in a set alarm mode according to an alarm strategy and alarm information configured by a user; performing problem detection and detailed log recording in each link of the dial-up test service flow, triggering a corresponding alarm mechanism to perform alarm notification processing, and performing notification alarm through correspondingly configured alarm modes (short messages, mails and telephones) and alarm levels according to the set alarm level; in the dial testing process, detailed dial testing process data and logs can be generated to be analyzed and processed by the service operation system, and for alarm notification, the system can automatically send the dial testing alarm condition to operation and maintenance personnel for processing, so that the whole operation monitoring closed-loop management is realized.
Wherein, after the dial testing is completed: the dial testing system provides detailed recording in the whole dial testing process, data in the dial testing process and a dial testing log, provides a data analysis and support basis for a service operation system, and provides help and guidance for optimizing and improving an intelligent operation dial testing process.
After the dial testing is completed, the detailed recording, the data in the dial testing process and the dial testing log of the whole dial testing process are stored, the information recording level is set, and a data analysis and support basis is provided for other business operation systems.
One specific application of this embodiment is:
the automatic dial testing method of the application file adopts a fool customized dial testing business process: the system upgrade provides form-guided customized dial testing service, and the form-guided customized dial testing service is converted into a dial testing process by a platform, so that the purpose of autonomously configuring the dial testing service process by operators is realized.
Before dial testing, dial testing service flows and dial testing parameters can be compiled in advance through a service flow editor, and the specific parameters comprise dial testing time, dial testing flows, alarm texts or voices, alarm threshold values, alarm notification levels and the like; through a self-defined dialing and testing process and a self-defined strategy, for the same navigation service process, the daytime and the evening are possibly different, and the morning and the evening are possibly different; the attention points at different times are different for operators, the dial testing frequency and the time-interval dial testing of the dial testing task can be configured, and the dial testing service time interval difference can be flexibly adapted; and simultaneously setting the threshold value of the alarm level: the system supports the configuration of the contents such as the alarm level, the alarm content, the alarm number and the like, supports the automatic selection of alarm in a short message or telephone form according to different alarm levels, and distinguishes emergency and general monitoring alarm according to the comparison of the actual index value and the set index threshold value.
When in dial testing, triggering the execution of dial testing tasks, carrying out dial testing according to dial testing processes by a dial testing system, carrying out analysis and judgment according to the standard flow trend of the dial testing service, and carrying out problem detection and detailed log recording on each link of the dial testing service processes and triggering a corresponding alarm mechanism to carry out alarm notification processing on links with problems; according to the set alarm level, the alarm is informed through the alarm modes (short messages, mails and telephones) and the alarm level which are correspondingly configured; and detailed dial testing process data and logs can be generated in the dial testing process and are analyzed and processed by the service operation system. For the alarm notification, the system can automatically send the alarm condition of the dial test to the operation and maintenance personnel for processing in time, thereby realizing the whole operation monitoring closed-loop management.
After the dial testing, the dial testing system provides detailed recording, data in the dial testing process and a dial testing log in the whole dial testing process, provides a data analysis and support basis for a service operation system, and provides help and guidance for optimizing and improving an intelligent operation dial testing process.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (5)
1. An automatic dial testing method for intelligent voice customer service is characterized by comprising the following steps:
step S1 creates an automatic dial testing task: the business process editor pre-compiles a dial testing business process and dial testing parameters, and creates and starts a dial testing task;
step S2 triggers the task to be dial: capturing voice audio stream in real time through an MRCP module of a GCPBX dial-test platform, and transmitting the voice audio stream to an MRCP server side through an MRCP protocol for audio real-time transcription;
step S3 semantic recognition processing analysis: transferring the transcription result to an intention processing module for semantic recognition processing and intention analysis, and recognizing further dial testing actions;
step S4 voice recording transcoding: transcoding the PCM file generated by the whole-course recording to generate a WAV file code conforming to the interface calling;
step S5 logging: and recording the process data of the voice dial test and the dial test log information and providing an interface service operation platform for calling, analyzing and processing.
2. The method as claimed in claim 1, wherein the preset dial-up parameters in step S1 include dial-up time, dial-up procedure, alarm text or voice, alarm threshold, alarm notification level.
3. The method as claimed in claim 1, wherein in step S3, the semantic recognition module includes inputting the recognized text, corpus collection, corpus training, corpus cleaning, format conversion, word segmentation or data set segmentation, model training, model evaluation or verification, model storage and intention recognition, and finally outputting the recognized intention result.
4. The automatic dial-up test method for intelligent voice customer service according to claim 1, wherein in the dial-up test process, when a fault or error occurs in any process step and an alarm mechanism is triggered, the alarm notification module notifies the operation and maintenance personnel in a set alarm manner according to the alarm strategy and alarm information configured by the user.
5. The method as claimed in claim 1, wherein after the completion of the dial testing, the detailed recording of the whole dial testing process, the data in the dial testing process, and the dial testing log are stored and the information recording level is set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911095755.3A CN110830661A (en) | 2019-11-11 | 2019-11-11 | Automatic dial testing method for intelligent voice customer service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911095755.3A CN110830661A (en) | 2019-11-11 | 2019-11-11 | Automatic dial testing method for intelligent voice customer service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110830661A true CN110830661A (en) | 2020-02-21 |
Family
ID=69553906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911095755.3A Pending CN110830661A (en) | 2019-11-11 | 2019-11-11 | Automatic dial testing method for intelligent voice customer service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110830661A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627448A (en) * | 2020-05-15 | 2020-09-04 | 公安部第三研究所 | System and method for realizing trial and talk control based on voice big data |
| CN113099044A (en) * | 2021-04-08 | 2021-07-09 | 中国工商银行股份有限公司 | Method, apparatus, device, medium and product for detecting incoming call device |
| CN113259531A (en) * | 2021-05-11 | 2021-08-13 | 中国工商银行股份有限公司 | Automatic voice service operation and maintenance method and system for call center |
| CN114466399A (en) * | 2021-12-20 | 2022-05-10 | 中盈优创资讯科技有限公司 | Automatic dial testing method and device for mobile service |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102572904A (en) * | 2011-12-28 | 2012-07-11 | 上海禹为通信技术有限公司 | System and method for implementing automatic dial test business |
| CN104363354A (en) * | 2014-10-29 | 2015-02-18 | 中国建设银行股份有限公司 | Detecting method and device for call center |
| CN106649694A (en) * | 2016-12-19 | 2017-05-10 | 北京云知声信息技术有限公司 | Method and device for identifying user's intention in voice interaction |
| US20170257482A1 (en) * | 2014-09-09 | 2017-09-07 | Cyara Solutions Pty Ltd | System and method for reliable call recording testing and proprietary customer information retrieval |
| CN107403619A (en) * | 2017-06-30 | 2017-11-28 | 武汉泰迪智慧科技有限公司 | A kind of sound control method and system applied to bicycle environment |
| CN107657017A (en) * | 2017-09-26 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Method and apparatus for providing voice service |
| CN109461440A (en) * | 2018-12-27 | 2019-03-12 | 广州云趣信息科技有限公司 | The method and smart machine of voice communication maximum possible intention are taken turns in a kind of acquisition more |
-
2019
- 2019-11-11 CN CN201911095755.3A patent/CN110830661A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102572904A (en) * | 2011-12-28 | 2012-07-11 | 上海禹为通信技术有限公司 | System and method for implementing automatic dial test business |
| US20170257482A1 (en) * | 2014-09-09 | 2017-09-07 | Cyara Solutions Pty Ltd | System and method for reliable call recording testing and proprietary customer information retrieval |
| CN104363354A (en) * | 2014-10-29 | 2015-02-18 | 中国建设银行股份有限公司 | Detecting method and device for call center |
| CN106649694A (en) * | 2016-12-19 | 2017-05-10 | 北京云知声信息技术有限公司 | Method and device for identifying user's intention in voice interaction |
| CN107403619A (en) * | 2017-06-30 | 2017-11-28 | 武汉泰迪智慧科技有限公司 | A kind of sound control method and system applied to bicycle environment |
| CN107657017A (en) * | 2017-09-26 | 2018-02-02 | 百度在线网络技术（北京）有限公司 | Method and apparatus for providing voice service |
| CN109461440A (en) * | 2018-12-27 | 2019-03-12 | 广州云趣信息科技有限公司 | The method and smart machine of voice communication maximum possible intention are taken turns in a kind of acquisition more |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111627448A (en) * | 2020-05-15 | 2020-09-04 | 公安部第三研究所 | System and method for realizing trial and talk control based on voice big data |
| CN113099044A (en) * | 2021-04-08 | 2021-07-09 | 中国工商银行股份有限公司 | Method, apparatus, device, medium and product for detecting incoming call device |
| CN113099044B (en) * | 2021-04-08 | 2022-11-18 | 中国工商银行股份有限公司 | Method, apparatus, device and medium for detecting incoming call device |
| CN113259531A (en) * | 2021-05-11 | 2021-08-13 | 中国工商银行股份有限公司 | Automatic voice service operation and maintenance method and system for call center |
| CN114466399A (en) * | 2021-12-20 | 2022-05-10 | 中盈优创资讯科技有限公司 | Automatic dial testing method and device for mobile service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110830661A (en) | Automatic dial testing method for intelligent voice customer service | |
| CN106550155B (en) | Swindle sample is carried out to suspicious number and screens the method and system sorted out and intercepted | |
| CN110197672B (en) | Voice call quality detection method, server and storage medium | |
| CN101010934B (en) | Method for machine learning | |
| CN107093431A (en) | A kind of method and device that quality inspection is carried out to service quality | |
| CN104240438A (en) | Method and device for achieving automatic alarming through mobile terminal and mobile terminal | |
| CN113468296B (en) | Model self-iteration type intelligent customer service quality inspection system and method capable of configuring business logic | |
| CN104301554A (en) | Device and method used for detecting service quality of customer service staff | |
| CN102067208A (en) | Methods and systems for measuring user performance with speech-to-text conversion for dictation systems | |
| CN108737182A (en) | The processing method and system of system exception | |
| CN109697243A (en) | Ring-back tone clustering method, device, medium and calculating equipment | |
| US20220303391A1 (en) | Systems and methods for prioritizing emergency calls | |
| CN110362545A (en) | Log monitoring method, device, terminal and computer readable storage medium | |
| CN112885376A (en) | Method and device for improving voice call quality inspection effect | |
| CN110245077A (en) | A kind of response method and equipment of program exception | |
| CN112511696A (en) | System and method for identifying bad content of call center AI engine | |
| US20200076707A1 (en) | Autonomic or AI-assisted validation, decision making, troubleshooting and/or performance enhancement within a telecommunications network | |
| CN112947902B (en) | System development management platform | |
| US20190213554A1 (en) | User support system with automatic message categorization | |
| CN114360533A (en) | Interaction method and system based on machine learning, elevator equipment and medium | |
| CN110166637A (en) | A kind of spacing recognition methods and device | |
| CN108717851A (en) | A kind of audio recognition method and device | |
| CN114546862A (en) | Dialogue test method and device, electronic equipment and computer readable storage medium | |
| CN114189589A (en) | Customer service outbound management system | |
| US7505569B2 (en) | Diagnosing voice application issues of an operational environment |
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 |
Application publication date: 20200221 |
|
| RJ01 | Rejection of invention patent application after publication |