CN112311937A - Customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition - Google Patents
Customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition Download PDFInfo
- Publication number
- CN112311937A CN112311937A CN202011025058.3A CN202011025058A CN112311937A CN 112311937 A CN112311937 A CN 112311937A CN 202011025058 A CN202011025058 A CN 202011025058A CN 112311937 A CN112311937 A CN 112311937A
- Authority
- CN
- China
- Prior art keywords
- customer service
- voice
- sip
- rtp
- packet
- 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
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000007689 inspection Methods 0.000 title claims abstract description 35
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 5
- 230000003139 buffering effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000009432 framing Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- H04M3/2227—Quality of service monitoring
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1101—Session protocols
- H04L65/1104—Session initiation protocol [SIP]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Quality & Reliability (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides a customer service real-time quality inspection method and a system based on SIP protocol packet capture and voice recognition, wherein the method comprises the following steps: a user dials a customer service center telephone to enter a customer service center soft switching platform; the customer service center soft switching platform selects a customer service IP phone through the network switch, and the user carries out voice communication with the selected customer service IP phone; the real-time quality inspection system acquires extension information of a user and a customer service and a voice stream of conversation by carrying out SIP and RTP port mirror image packet capturing on a customer service center soft switch platform on a mirror image port of a network switch; performing VAD breakpoint detection and voice recognition; matching the recognized words with the illegal word text, if matching information exists, giving an alarm, and/or hanging up the on-going phone. The method provided by the invention provides a real-time quality inspection function by using SIP packet capturing and voice recognition without changing the original system, can realize on-hook operation in time if necessary in the conversation process, and is real-time, comprehensive, efficient and low in cost compared with the original manual quality inspection.
Description
Technical Field
The invention relates to the field of customer service quality inspection, in particular to a customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition.
Background
At present, most of call center customer service mainly undertake product consultation, after-sale support, telemarketing, complaint receiving or government service and the like for enterprises, and in order to guarantee the service quality of the customer service and maintain the government image of the enterprises, quality inspection is very necessary to the conversation between the customer service and users in a call center customer service system. The prior art generally records the whole call between the customer service and the user, and the customer service chief manually checks and listens to the record after the call; thus, the method has higher randomness and incompleteness, but the method for performing quality inspection by audition one by one has high cost, low efficiency and poor feasibility; in addition, all the calls between the customer service and the user are recorded, so that a large storage resource is needed, and waste is caused; moreover, after the call is completed, the recording is checked and listened to, and the bad phenomena in the call process cannot be prevented in time, so that more troubles and losses are caused.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art and provides a customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition, which provide a real-time quality inspection function by using SIP packet capture and voice recognition under the condition of not changing the original system, can realize timely on-hook operation in the conversation process, is real-time, comprehensive, efficient and low in cost compared with the original manual quality inspection, and does not need to change the original customer service system.
The invention adopts the following technical scheme:
a customer service real-time quality inspection method based on SIP protocol packet capturing and voice recognition comprises the following steps:
a user dials a telephone of a customer service center through a telecom operator, enters a soft switch platform of the customer service center through an E1 line and a VoIP gateway of the telecom operator or directly enters the soft switch platform of the customer service center through an IMS line;
the customer service center soft switching platform selects a customer service IP phone through the network switch, and the user carries out voice communication with the selected customer service IP phone;
the real-time quality inspection system performs SIP and RTP port mirror image packet capturing on a customer service center soft switch platform on a mirror image port of a network switch to acquire a user number and extension number information of customer service, analyzes SDP content in an SIP message at the same time, acquires an RTP IP and a port of a user and customer service conversation, and acquires a conversation voice stream according to the RTP IP and the port;
after voice stream is cached and VAD breakpoint detection is carried out, submitting the voice stream to an ASR voice recognition engine platform for voice recognition;
matching the recognized words with illegal word texts configured in the database, if matching information exists, giving an alarm, and/or sending SIP messages to the customer service center soft switch platform and the customer service IP phone according to the configuration so as to hang up the ongoing call.
Specifically, parsing the SDP content in the SIP message, obtaining the IP and port of the RTP for the user to communicate with the customer service, and obtaining the voice stream of the session according to the IP and port of the RTP, specifically includes:
analyzing the packet captured by the SIP port, acquiring and storing from, to, contact, callld or tag information contained in the SIP head, acquiring and storing the IP and the port of the voice media RTP from the SDP, capturing the RTP voice stream according to the IP and the port of the RTP, and caching the captured voice stream in the voice queue.
Specifically, buffering a voice stream and then performing VAD endpoint detection includes:
the voice stream in the voice queue is obtained and decoded first,
background and noise are removed and voice VAD endpoint detection is performed.
Specifically, after submitting the ASR speech recognition engine platform for speech recognition, the method further includes:
meanwhile, the speech and the recognition result text are stored in the ASR speech recognition engine platform database, the database is updated, and the recognition rate of the ASR speech recognition engine platform is optimized.
Specifically, the hanging up of an ongoing phone by sending an SIP message to the customer service center soft switch platform and the customer service IP phone according to the configuration specifically includes:
and acquiring from, to, contact, call or tag information from the SIP head according to the configuration, and performing on-hook operation on the call of the user or the customer service by sending a BYE message of the SIP to the customer service center soft switch platform and the customer service IP phone according to the SIP protocol.
Specifically, the customer service real-time quality inspection method based on SIP protocol packet grabbing and voice recognition is executed in a LAN environment or a WAN environment.
The invention also provides a customer service real-time quality inspection system based on SIP protocol packet capturing and voice recognition, which is characterized in that: the method comprises the following steps: the device comprises an illegal word text configuration device, an SIP packet capturing device, an RTP packet capturing device, a voice stream cache queue device, a voice decoding device, a voice endpoint detection device, a voice recognition device, an acousto-optic alarm device and/or an SIP automatic on-hook device; specifically, the illegal word text configuration device is used for configuring the illegal word text to the database; the SIP packet capturing device is used for capturing packet information to the memory through the configured SIP parameters; the SIP analyzing device is used for analyzing the SIP packet which is captured by the SIP packet capturing device to obtain various SIP information parameters; the RTP packet capturing device is used for capturing the RTP voice stream packet to a memory voice stream buffer queue; the voice stream buffer queue device is used for buffering the RTP voice stream packet acquired by packet capturing of the RTP packet capturing device; the voice decoding device is used for decoding the RTP voice stream packet acquired by packet capturing; voice endpoint detection means for performing voice VAD endpoint detection on the voice decoded by the voice decoding means to obtain valid voice; the voice recognition device is used for recognizing the effective voice acquired by the voice endpoint detection device by using a voice recognition engine platform and matching the effective voice with the illegal language texts in the database configured in the illegal language text configuration device; the acousto-optic alarm device is used for carrying out acousto-optic alarm on the customer service when the text in the voice recognition device is matched; and the SIP automatic on-hook device is used for automatically on-hook the customer service or the user telephone when the text is matched in the voice recognition device.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
(1) the invention provides a customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition, which provide a real-time quality inspection function by using SIP packet capture and voice recognition without changing the original system, can realize timely on-hook operation in the conversation process if necessary, and is real-time, comprehensive, efficient and low in cost compared with the original manual quality inspection, and the original customer service system does not need to be changed.
(2) The real-time quality inspection system performs SIP and RTP port mirror image packet capturing on a customer service center soft switch platform on a mirror image port of a network switch to acquire a user number and extension number information of customer service, analyzes SDP content in an SIP message at the same time, acquires an RTP IP and a port of a user and customer service conversation, and acquires a conversation voice stream according to the RTP IP and the port; the method can acquire the voice information of the call between the user and the customer service in real time, does not need to modify the original customer service system module of the call center, and is simple, convenient and fast to operate through plug-in operation.
(3) Matching the recognized characters with illegal language texts configured in a database, if matching information exists, giving an alarm, and/or sending SIP messages to a customer service center soft switch platform and a customer service IP phone according to configuration so as to hang up the ongoing call; the bad phenomena in the conversation process are prevented in time, and the conditions of greater troubles and loss are avoided.
(4) After the ASR speech recognition engine platform is submitted for speech recognition, the speech and the recognition result text are simultaneously stored in the ASR speech recognition engine platform database, the database is updated, and the recognition rate of the ASR speech recognition engine platform can be optimized.
Drawings
FIG. 1 is a flowchart of an overall method of an embodiment of the present invention;
FIG. 2 is a block diagram of a customer service system of a customer service real-time quality inspection system with SIP protocol capture and speech recognition according to an embodiment of the present invention;
FIG. 3 is a block diagram of a customer service real-time quality inspection system with SIP protocol packet capture and speech recognition in an embodiment of the present invention.
The invention is described in further detail below with reference to the figures and specific examples.
Detailed Description
The invention is further described below by means of specific embodiments.
Fig. 1 is a flowchart of a method according to an embodiment of the present invention, and fig. 2 is a block diagram of a customer service operation system of a customer service real-time quality inspection system with SIP protocol capture and voice recognition, and a customer service real-time quality inspection method based on SIP protocol capture and voice recognition specifically includes:
s101: a user dials a telephone of a customer service center through a telecom operator, enters a soft switch platform of the customer service center through an E1 line and a VoIP gateway of the telecom operator or directly enters the soft switch platform of the customer service center through an IMS line;
a user dials a telephone of a customer service center through a mobile phone or a fixed telephone through a telecom operator, and enters a soft switch platform of the customer service center through an E1 line (a digital trunk line) and a VoIP line (a network telephone line) of the telecom operator, wherein one line of the E1 line can support 30 calls and can be bound with 30 different numbers, and one E1 line is equivalent to 30 analog telephone lines; the VoIP circuit converts an analog signal into a digital signal and transmits the digital signal on the network; of course, the service center soft switch platform can be directly accessed through the IMS line. The IMS line is a line based on a SIP registration core network and is introduced by China Mobile and China Unicom. The SIP protocol is an internet protocol and is not specified by a telecommunications expert or by an operator. The SIP-based call center is independent of access, accords with the development direction of network architecture evolution of various applications of a network to various access unified control core networks of various terminals, enables various services to be interacted simultaneously, forms a more flexible communication platform, and is also the line most suitable for a call center at present.
S102: the customer service center soft switching platform selects a customer service IP phone through the network switch, and the user carries out voice communication with the selected customer service IP phone;
a network switch is an equipment for enlarging network, which can provide more connection ports for sub-networks so as to connect more extensions. The method has the characteristics of high cost performance, high flexibility, relative simplicity, easy realization and the like. In this embodiment, the customer service center soft switch platform selects one of the connected customer service IP phones through the network switch, and the user makes a voice call with the selected customer service IP phone.
S103: the real-time quality inspection system performs SIP and RTP port mirror image packet capturing on a customer service center soft switch platform on a mirror image port of a network switch to acquire a user number and extension number information of customer service, analyzes SDP content in an SIP message at the same time, acquires an RTP IP and a port of a user and customer service conversation, and acquires a conversation voice stream according to the RTP IP and the port;
specifically, parsing the SDP content in the SIP message, obtaining the IP and port of the RTP for the user to communicate with the customer service, and obtaining the voice stream of the session according to the IP and port of the RTP, specifically includes:
analyzing the packet captured by the SIP port, acquiring and storing from, to, contact, callld or tag information contained in the SIP head, acquiring and storing the IP and the port of the voice media RTP from the SDP, capturing the RTP voice stream according to the IP and the port of the RTP, and caching the captured voice stream in the voice queue.
S104: after voice stream is cached and VAD breakpoint detection is carried out, submitting the voice stream to an ASR voice recognition engine platform for voice recognition;
specifically, buffering a voice stream and then performing VAD endpoint detection includes:
the voice stream in the voice queue is obtained and decoded first,
background and noise are removed and voice VAD endpoint detection is performed.
The VAD endpoint detection is mainly to accurately locate the start and end points of voice from noisy voice because voice contains long silence, i.e. the silence is separated from the actual voice; the method comprises the following specific steps: performing framing processing on the audio signal; extracting features from each frame of data; training a classifier on a set of data frames of a known speech and silence signal region; and classifying the unknown framing data, and judging whether the unknown framing data belongs to a voice signal or a silent signal.
Specifically, after submitting the ASR speech recognition engine platform for speech recognition, the method further includes:
meanwhile, the speech and the recognition result text are stored in the ASR speech recognition engine platform database, the database is updated, and the recognition rate of the ASR speech recognition engine platform is optimized.
S105: matching the recognized words with illegal word texts configured in the database, if matching information exists, giving an alarm, and/or sending SIP messages to the customer service center soft switch platform and the customer service IP phone according to the configuration so as to hang up the ongoing call.
The illegitimate use for text includes, but is not limited to, "cheating," "complaint," "fraud," "too bad," "so long," "contact N times," "make N calls," etc.; when the recognized characters can be matched with illegal phrase texts configured in the database, audible and visual alarm is carried out on the customer service, and corresponding customer service personnel are prompted to pay attention.
Specifically, the hanging up of an ongoing phone by sending an SIP message to the customer service center soft switch platform and the customer service IP phone according to the configuration specifically includes:
and acquiring from, to, contact, call or tag information from the SIP head according to the configuration, and performing on-hook operation on the call of the user or the customer service by sending a BYE message of the SIP to the customer service center soft switch platform and the customer service IP phone according to the SIP protocol.
Specifically, the customer service real-time quality inspection method based on SIP protocol packet grabbing and voice recognition is executed in a LAN environment or a WAN environment.
It is worth noting that the method provided by the invention is simple and convenient to operate by plug-in operation without modifying the original customer service system module of the call center.
Referring to fig. 3, another aspect of the present invention provides a customer service real-time quality inspection system based on SIP protocol packet capture and voice recognition, and another aspect of the present invention provides a customer service real-time quality inspection system based on SIP protocol packet capture and voice recognition, which is characterized in that: the method comprises the following steps: the device comprises an illegal word text configuration device, an SIP packet capturing device, an RTP packet capturing device, a voice stream cache queue device, a voice decoding device, a voice endpoint detection device, a voice recognition device, an acousto-optic alarm device and/or an SIP automatic on-hook device; specifically, the illegal word text configuration device is used for configuring the illegal word text to the database; the SIP packet capturing device is used for capturing packet information to the memory through the configured SIP parameters; the SIP analyzing device is used for analyzing the SIP packet which is captured by the SIP packet capturing device to obtain various SIP information parameters; the RTP packet capturing device is used for capturing the RTP voice stream packet to a memory voice stream buffer queue; the voice stream buffer queue device is used for buffering the RTP voice stream packet acquired by packet capturing of the RTP packet capturing device; the voice decoding device is used for decoding the RTP voice stream packet acquired by packet capturing; voice endpoint detection means for performing voice VAD endpoint detection on the voice decoded by the voice decoding means to obtain valid voice; the voice recognition device is used for recognizing the effective voice acquired by the voice endpoint detection device by using a voice recognition engine platform and matching the effective voice with the illegal language texts in the database configured in the illegal language text configuration device; the acousto-optic alarm device is used for carrying out acousto-optic alarm on the customer service when the text in the voice recognition device is matched; and the SIP automatic on-hook device is used for automatically on-hook the customer service or the user telephone when the text is matched in the voice recognition device.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.
Claims (7)
1. A customer service real-time quality inspection method based on SIP protocol packet capturing and voice recognition is characterized by comprising the following steps:
a user dials a telephone of a customer service center through a telecom operator, enters a soft switch platform of the customer service center through an E1 line and a VoIP gateway of the telecom operator or directly enters the soft switch platform of the customer service center through an IMS line;
the customer service center soft switching platform selects a customer service IP phone through the network switch, and the user carries out voice communication with the selected customer service IP phone;
performing SIP and RTP port mirror image packet capture on a customer service center soft switch platform on a mirror image port of a network switch to acquire a user number and extension number information of customer service, simultaneously analyzing SDP content in an SIP message, acquiring an RTP IP and a port of a user and customer service conversation, and acquiring a conversation voice stream according to the RTP IP and the port;
after voice stream is cached and VAD breakpoint detection is carried out, submitting the voice stream to an ASR voice recognition engine platform for voice recognition;
matching the recognized words with illegal word texts configured in the database, if matching information exists, giving an alarm, and/or sending SIP messages to the customer service center soft switch platform and the customer service IP phone according to the configuration so as to hang up the ongoing call.
2. The method for real-time quality inspection of customer service based on SIP protocol packet capture and voice recognition as claimed in claim 1, wherein the method comprises the steps of parsing SDP content in an SIP message, obtaining an IP and a port of an RTP for a user to communicate with the customer service, and obtaining a voice stream of a conversation according to the IP and the port of the RTP, and specifically comprises:
analyzing the packet captured by the SIP port, acquiring and storing from, to, contact, callld or tag information contained in the SIP head, acquiring and storing the IP and the port of the voice media RTP from the SDP, capturing the RTP voice stream according to the IP and the port of the RTP, and caching the captured voice stream in the voice queue.
3. The method according to claim 1, wherein the voice stream is buffered and then VAD endpoint detection is performed, and the method specifically includes:
the voice stream in the voice queue is obtained and decoded first,
background and noise are removed and voice VAD endpoint detection is performed.
4. The method of claim 1, wherein the step of submitting the ASR speech recognition engine platform for speech recognition further comprises:
meanwhile, the speech and the recognition result text are stored in the ASR speech recognition engine platform database, the database is updated, and the recognition rate of the ASR speech recognition engine platform is optimized.
5. The method for real-time quality inspection of customer service based on SIP protocol packet capture and voice recognition as claimed in claim 1, wherein the hanging up of the ongoing phone call by sending SIP message to the customer service center soft switch platform and the customer service IP phone according to the configuration specifically comprises:
and acquiring from, to, contact, call or tag information from the SIP head according to the configuration, and performing on-hook operation on the call of the user or the customer service by sending a BYE message of the SIP to the customer service center soft switch platform and the customer service IP phone according to the SIP protocol.
6. The method for real-time quality inspection of customer service based on SIP protocol bale plucking and voice recognition as claimed in claim 1, wherein the method for real-time quality inspection of customer service based on SIP protocol bale plucking and voice recognition is implemented in LAN environment or WAN environment.
7. A customer service real-time quality inspection system based on SIP protocol packet capturing and voice recognition is characterized in that: the method comprises the following steps: the device comprises an illegal word text configuration device, an SIP packet capturing device, an RTP packet capturing device, a voice stream cache queue device, a voice decoding device, a voice endpoint detection device, a voice recognition device, an acousto-optic alarm device and/or an SIP automatic on-hook device; specifically, the illegal word text configuration device is used for configuring the illegal word text to the database; the SIP packet capturing device is used for capturing packet information to the memory through the configured SIP parameters; the SIP analyzing device is used for analyzing the SIP packet which is captured by the SIP packet capturing device to obtain various SIP information parameters; the RTP packet capturing device is used for capturing the RTP voice stream packet to a memory voice stream buffer queue; the voice stream buffer queue device is used for buffering the RTP voice stream packet acquired by packet capturing of the RTP packet capturing device; the voice decoding device is used for decoding the RTP voice stream packet acquired by packet capturing; voice endpoint detection means for performing voice VAD endpoint detection on the voice decoded by the voice decoding means to obtain valid voice; the voice recognition device is used for recognizing the effective voice acquired by the voice endpoint detection device by using a voice recognition engine platform and matching the effective voice with the illegal language texts in the database configured in the illegal language text configuration device; the acousto-optic alarm device is used for carrying out acousto-optic alarm on the customer service when the text in the voice recognition device is matched; and the SIP automatic on-hook device is used for automatically on-hook the customer service or the user telephone when the text is matched in the voice recognition device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011025058.3A CN112311937A (en) | 2020-09-25 | 2020-09-25 | Customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011025058.3A CN112311937A (en) | 2020-09-25 | 2020-09-25 | Customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112311937A true CN112311937A (en) | 2021-02-02 |
Family
ID=74488676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011025058.3A Pending CN112311937A (en) | 2020-09-25 | 2020-09-25 | Customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112311937A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113395284A (en) * | 2021-06-16 | 2021-09-14 | 中国电信股份有限公司 | Multi-scene voice service real-time matching method, system, equipment and storage medium |
| CN114006889A (en) * | 2021-10-29 | 2022-02-01 | 迈普通信技术股份有限公司 | Voice gateway implementation method, voice gateway and IP voice communication system |
| CN114125160A (en) * | 2021-10-18 | 2022-03-01 | 中国人民解放军61623部队 | System and method for realizing real-time intelligent detection of voice service quality of manual desk |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1775716A1 (en) * | 2005-10-11 | 2007-04-18 | Deutsche Telekom AG | Procedure and system for obtaining quality indices for interactive voice response/natural language understanding (IVR/NLU) services |
| CN102137199A (en) * | 2011-03-31 | 2011-07-27 | 华为技术有限公司 | Method, device and system for call recording in call center |
| CN105719642A (en) * | 2016-02-29 | 2016-06-29 | 黄博 | Continuous and long voice recognition method and system and hardware equipment |
| US20170264575A1 (en) * | 2009-12-22 | 2017-09-14 | Cyara Solutions Pty Ltd | System and method for automated contact center agent workstation testing |
| CN108737667A (en) * | 2018-05-03 | 2018-11-02 | 平安科技（深圳）有限公司 | Voice quality detecting method, device, computer equipment and storage medium |
| CN111641757A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Real-time quality inspection and auxiliary speech pushing method for seat call |
| CN111681672A (en) * | 2020-05-26 | 2020-09-18 | 深圳壹账通智能科技有限公司 | Voice data detection method and device, computer equipment and storage medium |
-
2020
- 2020-09-25 CN CN202011025058.3A patent/CN112311937A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1775716A1 (en) * | 2005-10-11 | 2007-04-18 | Deutsche Telekom AG | Procedure and system for obtaining quality indices for interactive voice response/natural language understanding (IVR/NLU) services |
| US20170264575A1 (en) * | 2009-12-22 | 2017-09-14 | Cyara Solutions Pty Ltd | System and method for automated contact center agent workstation testing |
| CN102137199A (en) * | 2011-03-31 | 2011-07-27 | 华为技术有限公司 | Method, device and system for call recording in call center |
| CN105719642A (en) * | 2016-02-29 | 2016-06-29 | 黄博 | Continuous and long voice recognition method and system and hardware equipment |
| CN108737667A (en) * | 2018-05-03 | 2018-11-02 | 平安科技（深圳）有限公司 | Voice quality detecting method, device, computer equipment and storage medium |
| CN111641757A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Real-time quality inspection and auxiliary speech pushing method for seat call |
| CN111681672A (en) * | 2020-05-26 | 2020-09-18 | 深圳壹账通智能科技有限公司 | Voice data detection method and device, computer equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113395284A (en) * | 2021-06-16 | 2021-09-14 | 中国电信股份有限公司 | Multi-scene voice service real-time matching method, system, equipment and storage medium |
| CN113395284B (en) * | 2021-06-16 | 2022-12-30 | 中国电信股份有限公司 | Multi-scene voice service real-time matching method, system, equipment and storage medium |
| CN114125160A (en) * | 2021-10-18 | 2022-03-01 | 中国人民解放军61623部队 | System and method for realizing real-time intelligent detection of voice service quality of manual desk |
| CN114006889A (en) * | 2021-10-29 | 2022-02-01 | 迈普通信技术股份有限公司 | Voice gateway implementation method, voice gateway and IP voice communication system |
| CN114006889B (en) * | 2021-10-29 | 2024-04-16 | 迈普通信技术股份有限公司 | Voice gateway implementation method, voice gateway and IP voice communication system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112311937A (en) | Customer service real-time quality inspection method and system based on SIP protocol packet capture and voice recognition | |
| US10129394B2 (en) | Telephonic communication routing system based on customer satisfaction | |
| US7688954B2 (en) | System and method for identifying caller | |
| US7027986B2 (en) | Method and device for providing speech-to-text encoding and telephony service | |
| US6850602B1 (en) | Method and apparatus for answering machine detection in automatic dialing | |
| US20070263604A1 (en) | Ring back notification system and method therefor | |
| US8023639B2 (en) | Method and system determining the complexity of a telephonic communication received by a contact center | |
| US20060182232A1 (en) | System and method for the playing of key phrases in voice mail messages | |
| US20080240374A1 (en) | Method and system for linking customer conversation channels | |
| US20070263794A1 (en) | Method and apparatus for recording calls | |
| CN109417583A (en) | It is a kind of by audio signal real time transcription be text system and method | |
| EP1889257B1 (en) | A method and system for recording an electronic communication and extracting constituent audio data therefrom | |
| CN110620849A (en) | Centralized sorting method and system for IMS telephone terminal call records | |
| US8625577B1 (en) | Method and apparatus for providing audio recording | |
| US8078464B2 (en) | Method and system for analyzing separated voice data of a telephonic communication to determine the gender of the communicant | |
| CN108650425B (en) | Monitoring method and monitoring system | |
| CN110708418B (en) | Method and device for identifying attributes of calling party | |
| CN110519470A (en) | A kind of method of speech processing, server and audio access device | |
| CN115967789B (en) | Toll station telephone and monitoring video linkage method and system | |
| CN107888747B (en) | A kind of missed call message leaving method and device | |
| CN1774012A (en) | Testing method and tester for IP telephone sound quality | |
| CN117956111A (en) | Audio and video shunt touch system and method based on 5G video call | |
| CN116233080A (en) | Digital human video terminal adapting method, device, electronic equipment and storage medium | |
| CN112802477A (en) | Customer service assistant tool service method and system based on voice-to-text conversion | |
| CN117749875A (en) | Called party inter-vibrator multimedia display method based on direct connection MGCF node AS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210202 |