CN104427076A - Recognition method and recognition device for automatic answering of calling system - Google Patents
Recognition method and recognition device for automatic answering of calling system Download PDFInfo
- Publication number
- CN104427076A CN104427076A CN201310390449.9A CN201310390449A CN104427076A CN 104427076 A CN104427076 A CN 104427076A CN 201310390449 A CN201310390449 A CN 201310390449A CN 104427076 A CN104427076 A CN 104427076A
- Authority
- CN
- China
- Prior art keywords
- audio data
- automatic
- answering
- response packets
- back device
- 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
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
- H04M3/30—Automatic routine testing ; Fault testing; Installation testing; Test methods, test equipment or test arrangements therefor for subscriber's lines, for the local loop
Abstract
The invention discloses a recognition method and a recognition device for automatic answering of a calling system. The recognition method disclosed by the invention comprises the following steps: through an audio communication channel of answering equipment in the calling system, receiving an answering audio data packet, sent by the answering equipment, by a recognition server; analyzing the answering audio data packet by the recognition server so as to determine whether the answering audio data packet satisfies preset automatic answering parameters or not, and when whether the answering audio data packet satisfies the preset automatic answering parameters or not is determined, determining a voice answering type which corresponds to the answering audio data packet to be the automatic answering type by the recognition server. Automatic answering in called answering is recognized, so that the business process of the calling system is controlled by control equipment in the calling system according to a recognition result.
Description
Technical field
The present invention relates to the communications field, be related specifically to a kind of recognition methods and device of calling system automatic-answering back device.
Background technology
NGCC(Next Generation Call Center) calling system packet rows industry and abroad there are market prospects widely outside, this calling system carries out automatic speech typically by answering equipment and replys, and the part cannot carrying out replying for automatic speech then goes to manual service platform by manually being replied by answering equipment.
Calling system comprises control appliance, this control appliance controls the operation flow in calling system, this calling system also comprises identified server, media processing function in fundamental sum enhancing business is provided, for all media processings relevant to audio frequency and video, comprising Audio and Video RTP(RTP) data flow to the mutual conversion of video and audio file.Meanwhile, be also responsible for receiving user by the DTMF(dual-tone multifrequency of terminal) input, play service guiding voice, show dynamic guide picture.The SIP(text based agreement that it has) agreement and MSML(media session markup language and media object markup language)/MOML ability makes it can complete the mutual of whole conversation procedure and user under the control of application server APP.
This identified server can identify called party answer, Called Busy and nonreply.For in called party answer, have certain ratio to be automatic answering equipment, such as, comprise Modem(modulator-demodulator), fax, telephone message, voice mail and secretary's platform etc. need automatic answering equipment response to identify.But the part of automatic-answering back device in called party answer cannot identify by existing identified server.
Summary of the invention
Main purpose of the present invention, for providing a kind of recognition methods and device of calling system automatic-answering back device, is intended to realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
The present invention proposes a kind of recognition methods of calling system automatic-answering back device, and the method comprises:
When receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment;
Based on the voice communication channel set up, identified server receives the response packets of audio data that described answering equipment sends over;
Identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
Preferably, described when determining that described response packets of audio data meets default automatic-answering back device parameter, after identified server determines that voice answer-back type corresponding to described response packets of audio data is the step of automatic-answering back device, the method also comprises:
Voice answer-back type is that the recognition result of automatic-answering back device sends to control appliance in calling system by identified server, controls the operation flow of calling system to make described control appliance according to described recognition result.
Preferably, described when determining that described response packets of audio data meets default automatic-answering back device parameter, after identified server determines that voice answer-back type corresponding to described response packets of audio data is the step of automatic-answering back device, the method also comprises:
Identified server closes described voice communication channel, and carries out deletion detection to the data of preserving, and the data that will meet the deletion condition preset are deleted.
Preferably, described default automatic-answering back device parameter is default continuous quiet reference duration, and described identified server analyzes described response packets of audio data, to determine that the step whether described response packets of audio data meets automatic-answering back device parameter comprises:
Identified server obtains the continuous quiet duration of audio frequency from response packets of audio data;
When the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Preferably, when described default automatic-answering back device parameter is default continuous speech reference duration, described identified server analyzes described response packets of audio data, to determine that the step whether described response packets of audio data meets automatic-answering back device parameter comprises:
Identified server obtains the continuous speech duration of audio frequency from response packets of audio data;
When the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
The present invention also proposes a kind of recognition device of calling system automatic-answering back device, and this device comprises:
Data sending and receiving module, for when when receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment; And
Based on the voice communication channel set up, receive the response packets of audio data that described answering equipment sends over;
Identification module, for analyzing described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, determine that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
Preferably, described data sending and receiving module, also for being that the recognition result of automatic-answering back device sends to control appliance in calling system by voice answer-back type, controls the operation flow of calling system to make described control appliance according to described recognition result.
Preferably, this device also comprises processing module,
Described processing module, for closing described voice communication channel, and carry out deletion detection to the data of preserving, and the data that will meet the deletion condition preset is deleted.
Preferably, when described default automatic-answering back device parameter is default continuous quiet reference duration,
Described identification module, also for obtaining the continuous quiet duration of audio frequency from response packets of audio data; And
When the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Preferably, when described default automatic-answering back device parameter is default continuous speech reference duration,
Described identification module, also for obtaining the continuous speech duration of audio frequency from response packets of audio data; And
When the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Hinge structure, the present invention by set up with the voice communication channel of answering equipment in calling system, identified server receives the response packets of audio data that described answering equipment sends over; Identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
Accompanying drawing explanation
Fig. 1 is the particular flow sheet of the first embodiment of the recognition methods of calling system automatic-answering back device of the present invention;
Fig. 2 is the particular flow sheet of the second embodiment of the recognition methods of calling system automatic-answering back device of the present invention;
Fig. 3 is the particular flow sheet of the 3rd embodiment of the recognition methods of calling system automatic-answering back device of the present invention;
Fig. 4 is the particular flow sheet of the 4th embodiment of the recognition methods of calling system automatic-answering back device of the present invention;
Fig. 5 is the particular flow sheet of the first embodiment of the recognition device of calling system automatic-answering back device of the present invention;
Fig. 6 is the particular flow sheet of the second embodiment of the recognition device of calling system automatic-answering back device of the present invention.
The realization of the object of the invention, functional characteristics and advantage will in conjunction with the embodiments, are described further with reference to accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
As shown in Figure 1, be the particular flow sheet of the first embodiment of the recognition methods of calling system automatic-answering back device of the present invention.
It is emphasized that: flow chart shown in Fig. 1 is only a preferred embodiment, those skilled in the art is when knowing, any embodiment built around inventive concept should not depart from the scope contained in following technical scheme:
When receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment; Based on the voice communication channel set up, identified server receives the response packets of audio data that described answering equipment sends over; Identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
Below the concrete steps that the present embodiment progressively realizes the automatic-answering back device identifying answering equipment in calling system:
Step S11, when receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment.
Concrete, start the call flow of calling system, in calling system, answering equipment receives the media from telephone subscriber, and send called party answer packets of audio data based on the media of described reception, described answering equipment sends response to identified server and identifies request, when receiving response and identifying request, identified server sets up the voice communication channel with described answering equipment.In described calling system, answering equipment comprises at least one communication channel for receiving the media from telephone subscriber; The described corresponding communication channel being provided with response packets of audio data of communication channel for receiving from the media of telephone subscriber; Described identified server sets up the voice communication channel between described answering equipment respectively; Such as, when described answering equipment receives the media of telephone subscriber by A communication channel, described answering equipment sends called party answer packets of audio data based on the media of described reception, and the communication channel that described response packets of audio data sends is the B communication channel with A communication channel mapping settings; Described answering equipment sends response to identified server and identifies request, and when receiving response and identifying request, identified server sets up the voice communication channel with the B communication channel of described answering equipment; As mentioned above, identified server carrys out the voice communication channel of one_to_one corresponding foundation and described answering equipment according to the quantity of the communication channel of described answering equipment response packets of audio data.
Step S12, based on the voice communication channel set up, identified server receives the response packets of audio data that described answering equipment sends over.
Step S13, identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset.
Step S14, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
Concrete, based on the voice communication channel between the identified server set up and described answering equipment, identified server receives the response packets of audio data that described answering equipment sends over, identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device; When determining that described response packets of audio data does not meet the automatic-answering back device parameter preset, identified server determines that voice answer-back type corresponding to described response packets of audio data is for manual answering.In the present embodiment, described default automatic-answering back device parameter can be default quiet with reference to ratio, also can also be default continuous quiet with reference to duration or default continuous speech with reference to other automatic-answering back device parameters preset that can identify automatic-answering back device be suitable for arbitrarily for arranging in advance such as duration; In other embodiments of the present invention, described default automatic-answering back device parameter can also be the quiet reference ratio or continuous quiet with reference to duration or continuous speech reference duration etc. in preset time period, and described Preset Time can be the duration be suitable for that the users such as 30s or 40s are arranged in advance.Such as, voice communication channel C is established between the acknowledge communication channel B of identified server and described answering equipment, identified server receives response packets of audio data D from the acknowledge communication channel B C voice communication channel receipt of call system, described default automatic-answering back device parameter is quiet with reference to ratio for what preset, the quiet reference ratio preset is for 25%, identified server analyzes described response packets of audio data D, obtain the quiet ratio in this response packets of audio data D, if the quiet ratio in this response packets of audio data D obtained is 20%, the quiet ratio 20% obtained is less than default quiet reference ratio 25%, identified server determines that described response packets of audio data D meets default automatic-answering back device parameter, namely identified server determines that voice answer-back type corresponding to the response packets of audio data of described quiet ratio 20% is automatic-answering back device, if the quiet ratio in this response packets of audio data D obtained is 30%, the quiet ratio 30% obtained is greater than default quiet reference ratio 25%, identified server determines that described response packets of audio data D does not meet the automatic-answering back device parameter preset, and namely identified server determines that voice answer-back type corresponding to the response packets of audio data of described quiet ratio 30% is for manual answering.Voice answer-back type is that the recognition result of automatic-answering back device sends to control appliance in calling system by identified server, controls the operation flow of calling system to make described control appliance according to described recognition result.
By set up with the voice communication channel of answering equipment in calling system, identified server receives the response packets of audio data that described answering equipment sends over; Identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
As shown in Figure 2, be the particular flow sheet of the second embodiment of the recognition methods of calling system automatic-answering back device of the present invention.
Based on above-mentioned first embodiment, after step s 14, also comprise:
Step S15, identified server closes described voice communication channel, and carries out deletion detection to the data of preserving, and the data that will meet the deletion condition preset are deleted.
Concrete, when determining that described response packets of audio data meets default automatic-answering back device parameter, after identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device, identified server closes the voice communication channel set up between described and described answering equipment, and deletion detection is carried out to the data of preserving, the data that will meet the deletion condition preset are deleted.For the voice communication channel C set up between identified server and the acknowledge communication channel B of described answering equipment, the response packets of audio data D being received described answering equipment by voice communication channel C and send over, and after determining that described response packets of audio data D meets automatic-answering back device parameter, identified server closes described voice-grade channel channel C; Described default deletion condition can be that duration is preserved in the reference of preserving data, also can also be the parameter of other preservation data that user is arranged in advance, described default deletion condition preserves duration for the reference of preserving data, to the detection of the preservation duration of preservation data, if finding out the preservation duration preserving data is greater than with reference to preserving duration, then the described preservation data found out are deleted, described can be 10 days or 15 days with reference to preserving duration, also can also be that duration is preserved in other references that user is arranged in advance.In other embodiments of the present invention, can also be when Preset Time reaches, identified server carries out deletion to the data of preserving and detects, the data meeting the deletion condition preset are deleted, when not being confined to a closedown communication channel, identified server just carries out deletions detection to the data of preserving, and described Preset Time can be 1 day or 5 days, also can also be other arbitrary time spans of arranging in advance of user or time point.
By after the response packets of audio data receiving and identifying the transmission of described answering equipment, close the communication channel set up, reduce the running load of identified server, improve the speed of service, and by deleting the preservation data of identified server, the memory space of Appropriate application identified server, improves processing speed.
As shown in Figure 3, be the particular flow sheet of the 3rd embodiment of the recognition methods of calling system automatic-answering back device of the present invention.
Based on above-mentioned first embodiment, when described default automatic-answering back device parameter is default continuous quiet reference duration, step S13 also comprises:
Step S16, identified server obtains the continuous quiet duration of audio frequency from response packets of audio data.
Step S17, when the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Concrete, described default automatic-answering back device parameter is default continuous quiet reference duration, and described default continuous quiet reference duration can be set to 0.7s or 1.2s, also can also be that other any users detect by actual the time interval value drawn; for the continuous quiet reference duration preset for 0.7s, the response packets of audio data that the described answering equipment that identified server analysis receives sends over, the longest continuous quiet duration is obtained from the response packets of audio data of described reception, if the longest continuous quiet duration obtained is 0.6s, the longest continuous quiet duration then obtained is that 0.6s is less than default continuous quiet reference duration 0.7s, identified server determine described in the longest continuous quiet duration be that the response packets of audio data of 0.6s meets default automatic-answering back device parameter, namely identified server determines to grow most continuous quiet duration be voice answer-back type corresponding to the response packets of audio data of 0.6s is automatic-answering back device, if the longest continuous quiet duration obtained is 1.6s, the continuous quiet duration then obtained is that 1.6s is greater than continuous quiet reference duration 0.7s, identified server determine described in the longest continuous quiet duration be 1.6s response packets of audio data meet preset automatic-answering back device parameter, namely identified server determines to grow most continuous quiet duration be voice answer-back type corresponding to the response packets of audio data of 1.6s is manual answering.In other embodiments of the present invention, described default automatic-answering back device parameter can also be the continuous quiet reference duration preset in preset time period.
By analyzing described response packets of audio data, the longest continuous quiet duration is obtained from the response packets of audio data of described reception, when the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter, and determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
As shown in Figure 4, be the particular flow sheet of the 4th embodiment of the recognition methods of calling system automatic-answering back device of the present invention.
Based on above-mentioned first embodiment, when described automatic-answering back device parameter is continuous speech reference duration, step S13 also comprises:
Step S18, identified server obtains the continuous speech duration of audio frequency from response packets of audio data;
Step S19, when the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Concrete, described default automatic-answering back device parameter is default continuous speech reference duration, and described default continuous speech can be set to 3.0s or 4.0s with reference to duration, also can also be that other any users detect by actual the time interval value drawn, for the continuous speech preset reference duration for 3.0s, the response packets of audio data that in the described calling system that identified server analysis receives, answering equipment sends over, the longest continuous speech duration is obtained from the response packets of audio data of described reception, if the longest continuous speech duration obtained is 3.6s, the longest continuous speech duration then obtained is that 3.6s is greater than default continuous speech with reference to duration 3.0s, identified server determine described in the longest continuous speech duration be that the response packets of audio data of 3.6s meets default automatic-answering back device parameter, namely identified server determines that the longest continuous speech duration be voice answer-back type corresponding to the response packets of audio data of 3.6s is automatic-answering back device, if the longest continuous speech duration obtained is 1.6s, the continuous speech duration then obtained is that 1.6s is less than continuous speech with reference to duration 3.0s, identified server determine described in the longest continuous speech duration be that the response packets of audio data of 1.6s does not meet the automatic-answering back device parameter preset, namely identified server determines that the longest continuous speech duration be voice answer-back type corresponding to the response packets of audio data of 1.6s is manual answering.In other embodiments of the present invention, described default automatic-answering back device parameter can also be the continuous speech reference duration in preset time period.
By analyzing described response packets of audio data, the longest continuous speech duration is obtained from the response packets of audio data of described reception, when the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter, and determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
As shown in Figure 5, be the concrete Organization Chart of the first embodiment of the recognition device of calling system automatic-answering back device of the present invention.This device comprises data sending and receiving module 10 and identification module 20,
Described data sending and receiving module 10, for when receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment; And
Based on the voice communication channel set up, identified server receives the response packets of audio data that described answering equipment sends over.
Concrete, start the call flow of calling system, in calling system, answering equipment receives the media from telephone subscriber, and send called party answer packets of audio data based on the media of described reception, described answering equipment sends response to data sending and receiving module 10 and identifies request, when receiving response and identifying request, data sending and receiving module 10 sets up the voice communication channel with described answering equipment.Described answering equipment comprises at least one communication channel for receiving the media from telephone subscriber; The described corresponding communication channel being provided with response packets of audio data of communication channel for receiving from the media of telephone subscriber; Described data sending and receiving module 10 sets up the voice communication channel between described answering equipment respectively; Such as, when described answering equipment receives the media of telephone subscriber by A communication channel, described answering equipment sends called party answer packets of audio data based on the media of described reception, and the communication channel that described response packets of audio data sends is the B communication channel with A communication channel mapping settings; Described answering equipment sends response to data sending and receiving module 10 and identifies request, and when receiving response and identifying request, data sending and receiving module 10 sets up the voice communication channel with the B communication channel of described answering equipment; As mentioned above, data sending and receiving module 10 carrys out the voice communication channel of one_to_one corresponding foundation and described answering equipment according to the quantity of the communication channel of described answering equipment response packets of audio data.
Described identification module 20, for analyzing described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset; And
When determining that described response packets of audio data meets default automatic-answering back device parameter, determine that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
Concrete, based on set up and voice communication channel between described answering equipment, data sending and receiving module 10 receives the response packets of audio data that described answering equipment sends over, identification module 20 analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identification module 20 determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device; When determining that described response packets of audio data does not meet the automatic-answering back device parameter preset, identified server determines that voice answer-back type corresponding to described response packets of audio data is for manual answering.In the present embodiment, described default automatic-answering back device parameter can be default quiet with reference to ratio, also can also be default continuous quiet with reference to duration or default continuous speech with reference to other automatic-answering back device parameters preset that can identify automatic-answering back device be suitable for arbitrarily for arranging in advance such as duration; In other embodiments of the present invention, described default automatic-answering back device parameter can also be the quiet reference ratio or continuous quiet with reference to duration or continuous speech reference duration etc. in preset time period, and described Preset Time can be the duration be suitable for that the users such as 30s or 40s are arranged in advance.Such as, voice communication channel C is established between the acknowledge communication channel B of data sending and receiving module 10 and described answering equipment, data sending and receiving module 10 receives response packets of audio data D from the acknowledge communication channel B C voice communication channel receipt of call system, described default automatic-answering back device parameter is quiet with reference to ratio for what preset, the quiet reference ratio preset is for 25%, identification module 20 analyzes described response packets of audio data D, obtain the quiet ratio in this response packets of audio data D, if the quiet ratio in this response packets of audio data D obtained is 20%, the quiet ratio 20% that identification module 20 obtains is less than default quiet reference ratio 25%, identification module 20 determines that described response packets of audio data D meets default automatic-answering back device parameter, namely identification module 20 determines that voice answer-back type corresponding to the response packets of audio data of described quiet ratio 20% is automatic-answering back device, if the quiet ratio in this response packets of audio data D obtained is 30%, the quiet ratio 30% obtained is greater than default quiet reference ratio 25%, identification module 20 determines that described response packets of audio data D does not meet the automatic-answering back device parameter preset, and namely identification module 20 determines that voice answer-back type corresponding to the response packets of audio data of described quiet ratio 30% is for manual answering.Voice answer-back type is that the recognition result of automatic-answering back device sends to control appliance in calling system by data sending and receiving module 10, controls the operation flow of calling system to make described control appliance according to described recognition result.
By set up with the voice communication channel of answering equipment in calling system, data sending and receiving module 10 receives the response packets of audio data that described answering equipment sends over; Identification module 20 analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identification module 20 determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
As shown in Figure 6, be the concrete Organization Chart of the second embodiment of the recognition device of calling system automatic-answering back device of the present invention.This device comprises processing module 30,
Described processing module 30, for closing described voice communication channel, and carry out deletion detection to the data of preserving, and the data that will meet the deletion condition preset is deleted.
Concrete, when determining that described response packets of audio data meets default automatic-answering back device parameter, after identification module 20 determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device, processing module 30 closes the voice communication channel set up between described and described answering equipment, and deletion detection is carried out to the data of preserving, the data that will meet the deletion condition preset are deleted.That set up for data sending and receiving module 10 and set up between the acknowledge communication channel B of described answering equipment voice communication channel C, at the response packets of audio data D sended over by all described answering equipment of voice communication channel C reception, and after identification module 20 determines that described response packets of audio data D meets automatic-answering back device parameter, processing module 30 closes described voice-grade channel channel C; Described default deletion condition can be that duration is preserved in the reference of preserving data, also can also be the parameter of other preservation data that user is arranged in advance, described default deletion condition preserves duration for the reference of preserving data, processing module 30 is to the detection of the preservation duration of preservation data, if finding out the preservation duration preserving data is greater than with reference to preserving duration, then the described preservation data found out are deleted by processing module 30, described can be 10 days or 15 days with reference to preserving duration, also can also be that duration is preserved in other references that user is arranged in advance.In other embodiments of the present invention, can also be when Preset Time reaches, processing module 30 is carried out deletion to the data of preserving and is detected, the data meeting the deletion condition preset are deleted, when not being confined to a closedown communication channel, processing module 30 just carries out deletions detection to the data of preserving, and described Preset Time can be 1 day or 5 days, also can also be other arbitrary time spans of arranging in advance of user or time point.
By receive in data sending and receiving module 10 and by described in identification module identification answering equipment send response packets of audio data after, processing module 30 closes the communication channel set up, reduce the running load of described recognition device, improve the speed of service, and by deleting the preservation data of recognition device, the memory space of recognition device described in Appropriate application, improves processing speed.
Further, described identification module 20, also for obtaining the continuous quiet duration of audio frequency from response packets of audio data; And
When the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Concrete, described default automatic-answering back device parameter is default continuous quiet reference duration, and described default continuous quiet reference duration can be set to 0.7s or 1.2s, also can also be that other any users detect by actual the time interval value drawn; for the continuous quiet reference duration preset for 0.7s, the response packets of audio data that the described answering equipment that identification module 20 analysis receives sends over, the longest continuous quiet duration is obtained from the response packets of audio data of described reception, if the longest continuous quiet duration obtained is 0.6s, the longest continuous quiet duration then obtained is that 0.6s is less than default continuous quiet reference duration 0.7s, identification module 20 determine described in the longest continuous quiet duration be that the response packets of audio data of 0.6s meets default automatic-answering back device parameter, namely identification module 20 determines to grow most continuous quiet duration be voice answer-back type corresponding to the response packets of audio data of 0.6s is automatic-answering back device, if the longest continuous quiet duration obtained is 1.6s, the continuous quiet duration then obtained is that 1.6s is greater than continuous quiet reference duration 0.7s, identification module 20 determine described in the longest continuous quiet duration be 1.6s response packets of audio data meet preset automatic-answering back device parameter, namely identification module 20 determines to grow most continuous quiet duration be voice answer-back type corresponding to the response packets of audio data of 1.6s is manual answering.In other embodiments of the present invention, described default automatic-answering back device parameter can also be the continuous quiet reference duration preset in preset time period.
Described response packets of audio data is analyzed by identification module 20, the longest continuous quiet duration is obtained from the response packets of audio data of described reception, when the continuous quiet duration obtained is less than default continuous quiet reference duration, identification module 20 determines that described response packets of audio data meets default automatic-answering back device parameter, and determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
Further, described identification module 20, also for obtaining the continuous speech duration of audio frequency from response packets of audio data; And
When the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Concrete, described default automatic-answering back device parameter is default continuous speech reference duration, and described default continuous speech can be set to 3.0s or 4.0s with reference to duration, also can also be that other any users detect by actual the time interval value drawn, for the continuous speech preset reference duration for 3.0s, the response packets of audio data that in the described calling system that identification module 20 analysis receives, answering equipment sends over, the longest continuous speech duration is obtained from the response packets of audio data of described reception, if the longest continuous speech duration obtained is 3.6s, the continuous speech duration obtained is that 3.6s is greater than default continuous speech with reference to duration 3.0s, identification module 20 determine described in the longest continuous speech duration be that the response packets of audio data of 3.6s meets default automatic-answering back device parameter, namely identification module 20 determines that the longest continuous speech duration be voice answer-back type corresponding to the response packets of audio data of 3.6s is automatic-answering back device, if the longest continuous speech duration obtained is 1.6s, the continuous speech duration then obtained is that 1.6s is less than continuous speech with reference to duration 3.0s, identification module 20 determine described in the longest continuous speech duration be that the response packets of audio data of 1.6s does not meet the automatic-answering back device parameter preset, namely identification module 20 determines that the longest continuous speech duration be voice answer-back type corresponding to the response packets of audio data of 1.6s is manual answering.In other embodiments of the present invention, described default automatic-answering back device parameter can also be the continuous speech the preset reference duration in preset time period.
Described response packets of audio data is analyzed by identification module 20, the longest continuous speech duration is obtained from the response packets of audio data of described reception, when the continuous speech duration obtained is greater than default continuous speech with reference to duration, identification module 20 determines that described response packets of audio data meets default automatic-answering back device parameter, and determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.Realize the automatic-answering back device in called party answer to identify, with the operation flow making control appliance in calling system control calling system according to recognition result.
The foregoing is only the preferred embodiments of the present invention; not thereby the scope of the claims of the present invention is limited; every utilize specification of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.
Claims (10)
1. a recognition methods for calling system automatic-answering back device, is characterized in that, the method comprises:
When receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment;
Based on the voice communication channel set up, identified server receives the response packets of audio data that described answering equipment sends over;
Identified server analyzes described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, identified server determines that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
2. the recognition methods of calling system automatic-answering back device according to claim 1, it is characterized in that, described when determining that described response packets of audio data meets default automatic-answering back device parameter, after identified server determines that voice answer-back type corresponding to described response packets of audio data is the step of automatic-answering back device, the method also comprises:
Voice answer-back type is that the recognition result of automatic-answering back device sends to control appliance in calling system by identified server, controls the operation flow of calling system to make described control appliance according to described recognition result.
3. the recognition methods of calling system automatic-answering back device according to claim 1, it is characterized in that, described when determining that described response packets of audio data meets default automatic-answering back device parameter, after identified server determines that voice answer-back type corresponding to described response packets of audio data is the step of automatic-answering back device, the method also comprises:
Identified server closes described voice communication channel, and carries out deletion detection to the data of preserving, and the data that will meet the deletion condition preset are deleted.
4. the recognition methods of calling system automatic-answering back device according to claim 1 and 2, it is characterized in that, described default automatic-answering back device parameter is default continuous quiet reference duration, described identified server analyzes described response packets of audio data, to determine that the step whether described response packets of audio data meets automatic-answering back device parameter comprises:
Identified server obtains the continuous quiet duration of audio frequency from response packets of audio data;
When the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
5. the recognition methods of calling system automatic-answering back device according to claim 1 and 2, it is characterized in that, when described default automatic-answering back device parameter is default continuous speech reference duration, described identified server analyzes described response packets of audio data, to determine that the step whether described response packets of audio data meets automatic-answering back device parameter comprises:
Identified server obtains the continuous speech duration of audio frequency from response packets of audio data;
When the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
6. a device for the identification of calling system automatic-answering back device, is characterized in that, this device comprises:
Data sending and receiving module, for when receiving the response identification request that answering equipment in calling system sends, identified server sets up the voice communication channel with described answering equipment; And
Based on the voice communication channel set up, receive the response packets of audio data that described answering equipment sends over;
Identification module, for analyzing described response packets of audio data, to determine whether described response packets of audio data meets the automatic-answering back device parameter preset, when determining that described response packets of audio data meets default automatic-answering back device parameter, determine that voice answer-back type corresponding to described response packets of audio data is automatic-answering back device.
7. the recognition device of calling system automatic-answering back device according to claim 6, is characterized in that,
Described data sending and receiving module, also for being that the recognition result of automatic-answering back device sends to control appliance in calling system by voice answer-back type, controls the operation flow of calling system to make described control appliance according to described recognition result.
8. the recognition device of calling system automatic-answering back device according to claim 6, is characterized in that, this device also comprises processing module,
Described processing module, for closing described voice communication channel, and carry out deletion detection to the data of preserving, and the data that will meet the deletion condition preset is deleted.
9. the recognition device of the calling system automatic-answering back device according to claim 6 or 7, is characterized in that, when described default automatic-answering back device parameter is default continuous quiet reference duration,
Described identification module, also for obtaining the continuous quiet duration of audio frequency from response packets of audio data; And
When the continuous quiet duration obtained is less than default continuous quiet reference duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
10. the recognition device of the calling system automatic-answering back device according to claim 6 or 7, is characterized in that, when described default automatic-answering back device parameter is default continuous speech reference duration,
Described identification module, also for obtaining the continuous speech duration of audio frequency from response packets of audio data; And
When the continuous speech duration obtained is greater than default continuous speech with reference to duration, identified server determines that described response packets of audio data meets default automatic-answering back device parameter.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310390449.9A CN104427076A (en) | 2013-08-30 | 2013-08-30 | Recognition method and recognition device for automatic answering of calling system |
| PCT/CN2014/077731 WO2014173342A1 (en) | 2013-08-30 | 2014-05-16 | Method and device for identifying automatic response of calling system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310390449.9A CN104427076A (en) | 2013-08-30 | 2013-08-30 | Recognition method and recognition device for automatic answering of calling system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104427076A true CN104427076A (en) | 2015-03-18 |
Family
ID=51791072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310390449.9A Pending CN104427076A (en) | 2013-08-30 | 2013-08-30 | Recognition method and recognition device for automatic answering of calling system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104427076A (en) |
| WO (1) | WO2014173342A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107517207A (en) * | 2017-03-13 | 2017-12-26 | 平安科技（深圳）有限公司 | Server, auth method and computer-readable recording medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0688486A4 (en) * | 1993-01-14 | 1998-01-07 | Mci Telecommunications Corp | Telephone network performance monitoring method and system |
| CN1832515A (en) * | 2005-03-08 | 2006-09-13 | 华为技术有限公司 | Authorization system of automatic answering equipment and its authorization method |
| CN102082806A (en) * | 2009-11-26 | 2011-06-01 | 上海拜翰网络科技有限公司 | Method and system for pushing website navigation service through calling |
-
2013
- 2013-08-30 CN CN201310390449.9A patent/CN104427076A/en active Pending
-
2014
- 2014-05-16 WO PCT/CN2014/077731 patent/WO2014173342A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0688486A4 (en) * | 1993-01-14 | 1998-01-07 | Mci Telecommunications Corp | Telephone network performance monitoring method and system |
| CN1832515A (en) * | 2005-03-08 | 2006-09-13 | 华为技术有限公司 | Authorization system of automatic answering equipment and its authorization method |
| CN102082806A (en) * | 2009-11-26 | 2011-06-01 | 上海拜翰网络科技有限公司 | Method and system for pushing website navigation service through calling |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107517207A (en) * | 2017-03-13 | 2017-12-26 | 平安科技（深圳）有限公司 | Server, auth method and computer-readable recording medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2014173342A1 (en) | 2014-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110891124B (en) | System for artificial intelligence pick-up call | |
| CN103152740B (en) | A kind of anti-monitor method and system for mobile terminal | |
| CN102447782A (en) | Phone terminal capable of presenting phone conversation in conversation in real time | |
| US20070238451A1 (en) | Apparatus, method, computer program product and a data structure providing a contact list enhanced with a special contact indication for use in automatically generating a call back | |
| CN107241519A (en) | A kind of audio call centered video householder method and system | |
| US10313502B2 (en) | Automatically delaying playback of a message | |
| CN103227980A (en) | Information outputting method and device | |
| CN101360213B (en) | Method and apparatus for caller audio and video transmission before incoming call answering for visual telephone service | |
| KR20170073417A (en) | System for response correspond to mobile message | |
| JP2014504058A (en) | Network device, called terminal, and method for processing a third-party call | |
| CN104427076A (en) | Recognition method and recognition device for automatic answering of calling system | |
| CN111343328B (en) | Voice print recognition-based call management method and system and mobile terminal | |
| CN103259940A (en) | Communication terminal and message data transmission method | |
| WO2017166642A1 (en) | Mobile terminal redial method, device, and mobile terminal | |
| CN101964999B (en) | Voice quality enhancement method applied to satellite communication network | |
| CN105704327A (en) | Call rejection method and call rejection system | |
| CN101621482A (en) | Audio and video mail box device and realization method | |
| CN205622716U (en) | Network telephone system | |
| CN103108084A (en) | Anti-monitor method and system used for mobile terminal | |
| CA2647921A1 (en) | Method and system for configuring a contact database associated with a user | |
| CN109428803A (en) | A kind of method for sending voice message and system | |
| CN103595885B (en) | Domestic affection phone system | |
| US10818295B1 (en) | Maintaining network connections | |
| CN104184869A (en) | Method for realizing voice message function and home gateway | |
| US9514750B1 (en) | Voice call content supression |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20150318 |