[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN100496070C - Identification system of automatic answering equipment and its identification method - Google Patents

Identification system of automatic answering equipment and its identification method Download PDF

Info

Publication number
CN100496070C
CN100496070C CNB200510053601XA CN200510053601A CN100496070C CN 100496070 C CN100496070 C CN 100496070C CN B200510053601X A CNB200510053601X A CN B200510053601XA CN 200510053601 A CN200510053601 A CN 200510053601A CN 100496070 C CN100496070 C CN 100496070C
Authority
CN
China
Prior art keywords
signal
called subscriber
automatic answering
equipment
continuous
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.)
Expired - Fee Related
Application number
CNB200510053601XA
Other languages
Chinese (zh)
Other versions
CN1832515A (en
Inventor
朱祥文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CNB200510053601XA priority Critical patent/CN100496070C/en
Publication of CN1832515A publication Critical patent/CN1832515A/en
Application granted granted Critical
Publication of CN100496070C publication Critical patent/CN100496070C/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Telephonic Communication Services (AREA)

Abstract

This invention discloses an identifying system and its method for automatic response devices, in which, said system includes a customer service outer call device, a user signal character test device and an exchange access device and the user signal charcter test device carries out single-frequency signal test, a Fax pilot sequence test and continuous phone time test or continuous mute time test to called user signals, if the single frequency signal or the Fax pilot sequence is tested or if the continuous phone time and the mute time reach to a preset threshold value in said responding signals, then it is determined that the called user is the automatic responding device.

Description

The recognition system of automatic answering equipment and recognition methods thereof
Technical field
The present invention relates to the signal processing field, relate in particular to a kind of recognition system and recognition methods thereof of automatic answering equipment.
Background technology
In the service application of intelligent network, there are a large amount of outgoing call demands.The outer paging system of customer service initiatively makes a call to the user according to service needed.Customer service outgoing call system calling process is divided into effective outgoing call and invalid outgoing call, the calling of being answered by true man when effectively outgoing call is customer service paging system outgoing call outward; Invalid outgoing call be the outer paging system of customer service exhale outside run into called end in the process the line is busy, nobody replys, MODEM (modulator-demodulator) or facsimile machine is replied, Voice Mailbox, secretary's platform are replied etc., make outer paging system can't with the called calling that effectively exchanges.The outer paging system of customer service judges that according to called state or called signal type this time calling is effective call or infecctive call.If then transferring to this calling the operator, effective call handles; Infecctive call then temporarily skips over this calling if the line is busy, nobody replys etc., can promote outer paging system call completing rate of customer service and operator's efficient so greatly.
The equipment that MODEM, facsimile machine, Voice Mailbox, secretary's platform etc. can the automatic-answering back device customer service system be called out is called automatic answering equipment.
Outside at present numerous intelligent networks in the paging system, the line is busy, nobody replys etc. can detect and as the invalid outgoing call by signaling except called, also do not have a kind of effective detection method for automatic answering equipments such as MODEM sound, fax tone and Voice Mailbox, secretary's platforms, can't detect because this kind equipment is replied by signaling.Common way is to sacrifice efficient to ensure the quality of products, and soon automatic answering equipment is replied with true man and replied the operator attendance that all inserts the outer paging system of customer service, is handled by the operator, thereby causes the outgoing call call completing rate not high, and operator's efficient reduces.
Summary of the invention
The object of the present invention is to provide a kind of recognition system and recognition methods thereof of automatic answering equipment, can't discern automatic answering equipment with intelligent network customer service outgoing call equipment in the solution prior art and reply the problem of replying with true man.
For addressing the above problem, the invention provides following technical scheme:
A kind of recognition methods of automatic answering equipment, this method comprises the steps:
A, make a call and receive called subscriber's answer signal to the called subscriber;
B, at least described answer signal is carried out simple signal and detect, the fax leader detects, and in continuous speech time and three detections of continuous quiet time detecting one detects; If in described answer signal, detect simple signal, or detect the fax leader, or detect the continuous speech time and reach predetermined threshold value, determine that then the called subscriber is an automatic answering equipment.
Among the described step B,, then detect and determine whether called be automatic answering equipment by other one or two if can not determine earlier calledly during for automatic answering equipment by detection wherein.
Described step B comprises:
B1, the called subscriber answer signal is carried out simple signal detect,, determine that then the called subscriber be an automatic answering equipment if detect simple signal, otherwise commentaries on classics step B2;
B2, the called subscriber answer signal leader of faxing is detected,, determine that then the called subscriber be an automatic answering equipment if detect the fax leader, otherwise commentaries on classics step B3;
The continuous speech time and the continuous quiet time of B3, detection called subscriber answer signal, determine according to testing result whether called be automatic answering equipment.
The concrete steps that described simple signal detects are as follows:
A1, the called subscriber answer signal is done fast fourier transform, draws the amplitude spectrum of signal, from the signal amplitude spectrum, take out two maximum values | X (w 0) | 2| X (w 1) | 2
A2, if | X (w 0) | 2Greater than the signal amplitude peak value threshold, and | X (w 0) | 2-| X (w 1) | 2Greater than signal amplitude peak difference thresholding, and be consecutively detected w 0The duration of frequency signal then has simple signal in the called subscriber answer signal greater than time threshold.
Described time gate limit value is at least 100 milliseconds.
Described time gate limit value is 200 milliseconds.
The concrete steps that described fax leader detects are as follows:
B1, the called subscriber answer signal is carried out the frequency shift keying demodulation, the sequence after the demodulation is detected;
B2, if the sequence after demodulation in detect at least 3 V.21 lead codes of signal, then have the fax leader in the called subscriber answer signal.
The concrete steps of described continuous speech time and continuous quiet time detecting are as follows:
C1, the continuous speech time and the continuous quiet time of measuring the called subscriber answer signal;
C2, if continuous speech time of called subscriber answer signal greater than the continuous speech time threshold, then the called subscriber is an automatic answering equipment; If continuous speech time of called subscriber answer signal less than continuous speech time threshold and continuous quiet time greater than continuous quiet time threshold, then the called subscriber replys for true man.
Described continuous speech time gate limit value is 3 seconds.
Described continuous quiet time gate limit value is 0.7 second.
A kind of recognition system of automatic answering equipment comprises:
Customer service outgoing call equipment: be used for initiating outgoing call, determine according to the testing result of called subscriber answer signal whether needs insert operator attendance with the called subscriber to the called subscriber;
Subscriber signal feature detection equipment: be used for carrying out simple signal and detect by answer signal to the called subscriber, the fax leader detects, at least one that reaches in continuous speech time and three detections of continuous quiet time detecting is detected, and the identification called subscriber is true man or automatic answering equipment;
Exchange access device: connect customer service outgoing call equipment, subscriber signal feature detection equipment, called subscriber and operator attendance respectively, be used to transmit the signal between customer service outgoing call equipment, subscriber signal feature detection equipment and the called subscriber.
Described subscriber signal feature detection equipment comprises sound card and voice resource server, and sound card is inserted on the peripheral element interconnection slot of voice resource server.
Because the present invention has adopted above technical scheme, so have following beneficial effect:
The present invention detects by the called subscriber answer signal being carried out single-frequency class input, fax leader, whether in continuous speech time and the continuous quiet time detecting one or multinomial detection to offer an explanation the called subscriber be automatic answering equipment, thereby has improved the call completing rate of the outer paging system of customer service and operator's efficient.
Description of drawings
Fig. 1 is the structural representation of automatic answering equipment recognition system;
Fig. 2 is the workflow schematic diagram of automatic answering equipment recognition system;
Fig. 3 is the hardware configuration schematic diagram of sound card;
Fig. 4 gathers the schematic diagram of called subscriber answer signal for sound card;
Fig. 5 is the flow chart of automatic answering equipment recognition methods;
Fig. 6 is continuous speech time and continuous quiet time detecting schematic diagram.
Embodiment
As shown in Figure 1, automatic answering equipment recognition system of the present invention comprises:
Customer service outgoing call equipment: be used for making a call, determine according to the testing result of called subscriber's signal whether needs insert operator attendance with called subscriber's signal to the called subscriber;
Subscriber signal feature detection equipment: detect the feature of called subscriber answer signal under the control of customer service outgoing call equipment, the identification called subscriber is true man or automatic answering equipment;
Exchange access device: connect customer service outgoing call equipment, subscriber signal feature detection equipment, called subscriber and operator attendance respectively, be used to transmit the data-signal between customer service outgoing call equipment, subscriber signal feature detection equipment and the called subscriber.
Control signal between customer service outgoing call equipment, exchange access device, subscriber signal feature detection equipment and the operator attendance is by TCP/IP (Transfer Control Protocol/Internet Protocol, transmission control protocol agreement/Internet protocol) connection communication; Pass through the Signaling System Number 7 connection communication between exchange access device and the switching network; Data-signal between exchange access device, subscriber signal feature detection equipment and the operator attendance is by E1 interface connection communication.
As shown in Figure 2, the fine rule among the figure is represented control signal, and thick line is represented data-signal.Customer service outgoing call equipment makes a call to the called subscriber by switching network, the exchange access device sends IAI (initial address) message to the called subscriber, after the exchange access device receives ACM (called free time) message and ANM (called off-hook) message that the called subscriber returns by switching network, customer service outgoing call Equipment Control exchange access device is sent called party data into subscriber signal feature detection equipment, and issues the order that starts the subscriber signal feature detection to subscriber signal feature detection equipment.It is true man or automatic answering equipment that subscriber signal feature detection equipment goes out the active user according to the called party data feature identification, and by the exchange access device testing result is reported customer service outgoing call equipment.If testing result shows that the called subscriber is true man, then customer service outgoing call equipment sends the order that inserts the called subscriber to operator attendance, and by the exchange access device user data is inserted operator attendance, by operator attendance and called subscriber's conversation; If testing result shows that the called subscriber is an automatic answering equipment equipment, then customer service outgoing call Equipment Control exchange access device discharges this calling, and customer service outgoing call equipment is ignored this calling.If nobody replys called subscriber busy or called subscriber, then callee side can send REL (release) message to the exchange access device, carry Called Busy or the called cause value that nobody replys in the message, the exchange access device is with release cause value notice customer service outgoing call equipment, and customer service outgoing call equipment is ignored this calling.
Subscriber signal feature detection equipment comprises sound card and voice resource server, sound card directly is inserted in PCI (the Peripheral Component Interconnect of voice resource server, peripheral element interconnection) on the slot, the driver of sound card is installed on the voice resource server.
As shown in Figure 3, the structure of sound card comprises DSP (Digital Signal Processing, digital signal processor) and CPU (Central Processing Unit, CPU), sound card is by E1 or HW (High Wire, high-speed bus) interface connects the exchange access device, and the CPU of sound card connects the voice resource server by pci interface.After the voice resource server sends the order of start detection subscriber signal feature to DSP, the user data that the exchange access device inserts is given DSP by HW, DSP detects user data, judge that the user is true man or automatic answering equipment, and judged result reported CPU by the HPI bus, CPU reports the voice resource server by pci interface with the recognition result of DSP.
As shown in Figure 4, the process of the DSP of sound card identification automatic answering equipment comprises simple signal detection, fax leader detection and continuous speech and three parts of continuous quiet time detecting.The data source of above-mentioned three kinds of detection modes is identical, all is that the exchange access device is given the user data of DSP by HW, and this user data leaves in the 10ms data buffer zone of DSP.
At least need in the present invention called subscriber's answer signal is carried out the simple signal detection, the fax leader detects, and a detection in continuous speech time and the continuous quiet time detecting; If in answer signal, detect simple signal, or detect the fax leader, or detect the continuous speech time and the continuous quiet time reaches predetermined threshold value, determine that then the called subscriber is an automatic answering equipment.
As shown in Figure 5, describe with the detailed process of a preferred embodiment below the automatic answering equipment recognition methods:
At first the called subscriber answer signal is carried out simple signal and detect, be mainly used in and detect the simple signal that automatic answering equipment sends.Automatic answering equipments such as fax, MODEM can send the equifrequent simple signal of 2100Hz after connection, and adopt the automatic answering equipment of North America standard can produce 3 special simple signal sequences, first sequence tone is 913.8Hz or 985.2Hz, second sequence tone is 1370.6Hz or 1428.5Hz, the 3rd sequence tone be 1776.7Hz always, preceding two tone durations are 274 or 380ms, the 3rd tone be 380ms always, the amplitude of three tones is followed successively by-8dBm0,-9dBm0 ,-10dBm0.
The purpose that simple signal detects is to detect the frequency of the simple signal that called subscriber equipment sent, the exchange subscriber signal that access device inserted is FFT (the Fast Fourier Transform of 256 points, fast fourier transform) analyzes, calculate the amplitude spectrum of signal, and the size of amplitude spectrum is sorted.Definition signal amplitude peak thresholding is L1, the signal amplitude peak value is the amplitude peak value in the signal amplitude spectrum, signal amplitude peak difference thresholding is L2, the signal amplitude peak difference is the amplitude difference between two range values maximum in the signal amplitude spectrum, takes out two maximum values from the amplitude spectrum of signal: | X (w 0) | 2| X (w 1) | 2If, | X (w 0) | 2L1, and | X (w 0) | 2-| X (w 1) | 2L2, and be consecutively detected w 0The duration of frequency signal is greater than time threshold T, time threshold T is at least 100ms, the general 200ms that selects, then subscriber signal feature detection equipment reports to customer service outgoing call equipment and detects simple signal, and wherein w0 is exactly the frequency of automatic answering equipment answer signal.
Adopt the FFT method to carry out single-frequency class input and can detect the interior optional frequency signal of 300-4000Hz scope.
Because some facsimile machine is being replied Shi Buhui generation simple signal, and directly sends the fax leader, the lead code flag (0x7E) after promptly V.21 signal is modulated.For this class facsimile machine, owing to there is not simple signal to produce, can not detect by single-frequency class signal detecting method, the leader of can only faxing detects.V.21 signal uses FSK (Frequency Shift Keying, frequency shift keying) modulator approach, carrier frequency is 1750Hz, sample frequency 8000Hz, baud rate 300bit/s, be encoded to 0 Bit data and be modulated into the signal that frequency is 1850Hz, be encoded to 1 Bit data and be modulated into the signal that frequency is 1650Hz.V.21 the lead code flag of signal is the continuous 0x7E of about 1s (01111110), is the lead code before any V.21 signal modulated control frame.To V.21 by FSK coherent demodulation method, signal reverts to 0 and 1 preceding sequence of modulation, (individual 1 of 160-12~160+14) is " 111111 " among the 0x7E as having in the infructescence continuously, (53-12~53+14) is individual 0, then is " 00 " among the 0x7E as having in the infructescence continuously.As continuous 3 0x7E are arranged in the infructescence, then subscriber signal feature detection equipment reports to customer service outgoing call equipment and detects V.21 leader.
If both there be not simple signal in the subscriber signal, there is not V.21 leader signal again, think that then subscriber signal is a voice signal, need analyze voice signal, further identification is that true man talk or the voice that machine is play.True man have colloquial word or expression in a minute usually, as " feeding ", " you are good " etc., have the long dead time to wait for the other side's response thereafter, and its quiet time interval is bigger, and general machine talk all is continuous, and its quiet time interval is less.By statistics, the response time that general true man speak is thereafter the dead time greater than 0.7s less than 1.5s; And the continuous speech time of general automatic answering equipment is usually more than 3s.
As shown in Figure 6, setting the continuous speech time threshold is M1, and the preferred value of M1 is 3s, continuous quiet time threshold is M2, the preferred value of M2 is 0.7s, if the continuous speech time that detects subscriber signal greater than continuous speech time threshold M1, then the called subscriber is an automatic answering equipment; If the continuous speech time that detects subscriber signal less than the threshold value M1 that sets and continuous quiet time greater than the threshold value M2 that sets, then the called subscriber replys for true man.
Measure the continuous speech time and the continuous quiet time of called subscriber answer signal, concrete steps are as follows:
A, every 10ms user voice signal are a frame, calculate the average short-time energy Short_Energy (i) and the zero-crossing rate Rate_Cross_Zero (i) of a frame voice signal;
Energy Long_Energy (i) during B, signal calculated average long, Long_Energy (i)=(1-β) * Long_Energy (i-1)+β * Short_Energy (i), wherein β is a smoothing factor, gets β=1/16 here;
C, calculating noise energy Noise_Energy, setting noise energy max threshold thresholding NOISE_MAX_ENERGY_THRESHOLD (be generally-30dBm~-40dBm), noise energy minimum threshold thresholding NOISE_MIN_ENERGY_THRESHOLD (be generally less than-40dBm).If energy is less than the noise energy maximum threshold during Chief Signal Boatswain, and zero-crossing rate is greater than 10 or less than 3, energy when then noise energy being updated to Chief Signal Boatswain, if the noise energy after the noise energy after upgrading less than noise energy minimum threshold thresholding, is then upgraded equals noise energy minimum threshold thresholding;
The program of calculating noise energy is as follows:
if((Long_Energy(i)<NOISE_MAX_ENERGY_THRESHOLD)
&&((Rate_Cross_Zero(i)>10)‖(Rate_Cross_Zero(i)<3)))
Noise_Energy=Long_Energy(i);
if(Noise_Energy<NOISE_MIN_ENERGY_THRESHOLD)
Noise_Energy=NOISE_MIN_ENERGY_THRESHOLD;
endif
endif
D, detect the starting point of user voice signal, set speech signal energy thresholding thresholding and be SPEECH_ENERGY_THRESHOLD (be generally-20dBm~-30dBm), if energy Long_Energy (i) is greater than speech signal energy thresholding thresholding during signal long, zero-crossing rate Rate_Cross_Zero (i) is more than or equal to 3, be less than or equal to 10, signal to noise ratio Long_Energy (i)/Noise_Energy 〉=4 (12dB), and lasting frame number Speech_Start_Flag_Frame_Counter is greater than 3 frames, satisfy this condition and think the starting point that detects voice, voice beginning flag Speech_Start_Flag=1 is set, and the duration Speech_Continue_Time_Counter of beginning computing voice;
The specific procedure that detects the user speech starting point is as follows:
Put initial value:
Speech_Start_Flag_Frame_Counter=0;
Speech_Start_Flag=0;
Speech_Continue_Time_Counter=0;
The every 10ms of following process calculates once
if((Long_Energy(i)>SPEECH_ENERGY_THRESHOLD)&&
((Rate_Cross_Zero(i)<=10)&&(Rate_Cross_Zero(i)>=3))&&
((Long_Energy(i)/Noise_Energy)>=4)))
Speech_Start_Flag_Frame_Counter++;
else
Speech_Start_Flag_Frame_Counter=0;
endif
if(Speech_Start_Flag_Frame_Counter>3)
Speech_Start_Flag=1;
endif
if(Speech_Start_Flag==1)
Speech_Continue_Time_Counter++;
endif
The maximum Max_Long_Energy of energy when E, signal calculated length, the initial value Max_Long_Energy of energy is changed to 0 during with Chief Signal Boatswain, and the every 10ms of following process calculates once:
if(Speech_Start_Flag==1)
if(Long_Energy(i)>Max_Long_Energy)
Max_Long_Energy=Long_Energy(i)
endif
endif
The end point of F, detection user voice signal, if the ratio of energy Long_Energy (i) was greater than 4 (12dB) when energy maximum Max_Long_Energy and signal averaging were long during Chief Signal Boatswain, think that then voice finish, and beginning computing voice quiet continuous time of Speech_Silence_Time_Counter;
if(Speech_Start_Flag==1)
if((Max_Long_Energy/Long_Energy(i))>4)
Speech_Silence_Time_Counter++;
else
Speech_Silence_Time_Counter=0;
endif
endif
If less than M1 (3s), then report the called subscriber to customer service outgoing call equipment is true man to continuous quiet time Speech_Silence_Time_Counter greater than quiet time threshold M2 (0.7s) and continuous speech time Speech_Continue_Time_Counter; If continuous speech time Speech_Continue_Time_Counter is more than or equal to M1 (3s), then reporting the called subscriber to customer service outgoing call equipment is automatic answering equipment.
Parameters such as above-mentioned noise energy thresholding, speech signal energy thresholding, continuous speech time, continuous quiet time, signal to noise ratio can be configured by the user.
Below only the present invention will be described with preferred embodiment, and those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these are revised and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also is intended to comprise these changes and modification interior.

Claims (12)

1, a kind of recognition methods of automatic answering equipment is characterized in that, this method comprises the steps:
A, make a call and receive called subscriber's answer signal to the called subscriber;
B, at least described answer signal is carried out simple signal and detect, the fax leader detects, and in continuous speech time and three detections of continuous quiet time detecting one detects; If in described answer signal, detect simple signal, or detect the fax leader, or detect the continuous speech time and reach predetermined threshold value, determine that then the called subscriber is an automatic answering equipment.
2, the recognition methods of automatic answering equipment according to claim 1, it is characterized in that, among the described step B,, then detect and determine whether called be automatic answering equipment by other one or two if can not determine earlier calledly during for automatic answering equipment by detection wherein.
3, the recognition methods of automatic answering equipment according to claim 2 is characterized in that, described step B comprises:
B1, the called subscriber answer signal is carried out simple signal detect,, determine that then the called subscriber be an automatic answering equipment if detect simple signal, otherwise commentaries on classics step B2;
B2, the called subscriber answer signal leader of faxing is detected,, determine that then the called subscriber be an automatic answering equipment if detect the fax leader, otherwise commentaries on classics step B3;
The continuous speech time and the continuous quiet time of B3, detection called subscriber answer signal, determine according to testing result whether called be automatic answering equipment.
According to the recognition methods of claim 1 or 2 or 3 described automatic answering equipments, it is characterized in that 4, the concrete steps that described simple signal detects are as follows:
A1, the called subscriber answer signal is done fast fourier transform, draws the amplitude spectrum of signal, from the signal amplitude spectrum, take out two maximum values | X (w 0) | 2| X (w 1) | 2
A2, if | X (w 0) | 2Greater than the signal amplitude peak value threshold, and | X (w 0) | 2-| X (w 1) | 2Greater than signal amplitude peak difference thresholding, and be consecutively detected w 0The duration of frequency signal then has simple signal in the called subscriber answer signal greater than time threshold.
5, the recognition methods of automatic answering equipment according to claim 4 is characterized in that, described time gate limit value is at least 100 milliseconds.
6, the recognition methods of automatic answering equipment according to claim 4 is characterized in that, described time gate limit value is 200 milliseconds.
According to the recognition methods of claim 1 or 2 or 3 described automatic answering equipments, it is characterized in that 7, the concrete steps that described fax leader detects are as follows:
B1, the called subscriber answer signal is carried out the frequency shift keying demodulation, the sequence after the demodulation is detected;
B2, if the sequence after demodulation in detect at least 3 V.21 lead codes of signal, then have the fax leader in the called subscriber answer signal.
According to the recognition methods of claim 1 or 2 or 3 described automatic answering equipments, it is characterized in that 8, the concrete steps of described continuous speech time and continuous quiet time detecting are as follows:
C1, the continuous speech time and the continuous quiet time of measuring the called subscriber answer signal;
C2, if continuous speech time of called subscriber answer signal greater than the continuous speech time threshold, then the called subscriber is an automatic answering equipment; If continuous speech time of called subscriber answer signal less than continuous speech time threshold and continuous quiet time greater than continuous quiet time threshold, then the called subscriber replys for true man.
9, the recognition methods of automatic answering equipment according to claim 8 is characterized in that: described continuous speech time gate limit value is 3 seconds.
10, the recognition methods of automatic answering equipment according to claim 8 is characterized in that: described continuous quiet time gate limit value is 0.7 second.
11, a kind of recognition system of automatic answering equipment is characterized in that, comprising:
Customer service outgoing call equipment: be used for initiating outgoing call, determine according to the testing result of called subscriber answer signal whether needs insert operator attendance with the called subscriber to the called subscriber;
Subscriber signal feature detection equipment: be used for carrying out simple signal and detect by answer signal to the called subscriber, the fax leader detects, at least one that reaches in continuous speech time and three detections of continuous quiet time detecting is detected, and the identification called subscriber is true man or automatic answering equipment;
Exchange access device: connect customer service outgoing call equipment, subscriber signal feature detection equipment, called subscriber and operator attendance respectively, be used to transmit the signal between customer service outgoing call equipment, subscriber signal feature detection equipment and the called subscriber.
12, the recognition system of automatic answering equipment according to claim 11 is characterized in that, described subscriber signal feature detection equipment comprises sound card and voice resource server, and sound card is inserted on the peripheral element interconnection slot of voice resource server.
CNB200510053601XA 2005-03-08 2005-03-08 Identification system of automatic answering equipment and its identification method Expired - Fee Related CN100496070C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNB200510053601XA CN100496070C (en) 2005-03-08 2005-03-08 Identification system of automatic answering equipment and its identification method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNB200510053601XA CN100496070C (en) 2005-03-08 2005-03-08 Identification system of automatic answering equipment and its identification method

Publications (2)

Publication Number Publication Date
CN1832515A CN1832515A (en) 2006-09-13
CN100496070C true CN100496070C (en) 2009-06-03

Family

ID=36994499

Family Applications (1)

Application Number Title Priority Date Filing Date
CNB200510053601XA Expired - Fee Related CN100496070C (en) 2005-03-08 2005-03-08 Identification system of automatic answering equipment and its identification method

Country Status (1)

Country Link
CN (1) CN100496070C (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101287029A (en) * 2007-04-13 2008-10-15 华为技术有限公司 Method and apparatus for automatically respond to detection
CN101662544B (en) * 2008-08-26 2012-01-25 华为技术有限公司 Method, device and system for external-call processing
CN101668090B (en) * 2008-09-05 2012-07-04 华为技术有限公司 Text telephone detection method and device, and outbound detection system
CN102739557B (en) * 2011-04-08 2016-06-22 腾讯科技(深圳)有限公司 User's shunt method in customer service and device
CN103295585A (en) * 2012-02-24 2013-09-11 北京英立讯科技有限公司 Processing system and method identifying whether telephone automatic dialing is responded by real human
CN104427076A (en) * 2013-08-30 2015-03-18 中兴通讯股份有限公司 Recognition method and recognition device for automatic answering of calling system
CN109587358A (en) * 2017-09-29 2019-04-05 吴杰 Artificial intelligence customer service turns artificial customer service call method
CN109873907B (en) * 2019-03-29 2021-06-08 彭舒婷 Call processing method, device, computer equipment and storage medium
CN111586258B (en) * 2020-04-21 2022-04-19 深圳震有科技股份有限公司 Method, system and storage medium for completing fax call based on fax gateway
CN111885269B (en) * 2020-06-30 2021-07-20 马上消费金融股份有限公司 Information detection method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN1832515A (en) 2006-09-13

Similar Documents

Publication Publication Date Title
US20070263604A1 (en) Ring back notification system and method therefor
KR100614910B1 (en) Method for setting up a voice call and method of indicating that an internet communication has arrived
AU760141B2 (en) Digital signal processor-based telephone test set analysing and displaying multiple signal parameter data for terminal mode and line monitor mode operation
CN101208942B (en) Method for protection against undesirable telemarketing advertisements for communication networks
DE60228834D1 (en) SYSTEM AND METHOD FOR RECEIVING TELEPHONE CONNECTIONS THROUGH INSTANT MESSAGING
CN100496070C (en) Identification system of automatic answering equipment and its identification method
KR20010021158A (en) Method for prequalifying subscriber lines for high speed data service
CN103227980A (en) Information outputting method and device
US5949864A (en) Fraud prevention apparatus and method for performing policing functions for telephone services
US6519250B1 (en) Quick connect internet telephone and method therefor
US4995076A (en) Call progress capability for a switched channel data service unit
CN104618593B (en) A kind of operating method when mobile terminal and its third party&#39;s incoming call
US6118857A (en) Modem
CN101127777A (en) Method, device and system for processing security threat information of voice communication
EP1889257A1 (en) A method and system for recording an electronic communication and extracting constituent audio data therefrom
CN107968731B (en) The aobvious number method for detecting abnormality of one kind and server
US20030095544A1 (en) Method and apparatus for low-latency, semantic conveyance of an answer tone over a data network
CN110379444A (en) Detection method and device, the electronic equipment of telephone state are judged by preposition media
CN111884886B (en) Intelligent household communication method and system based on telephone
US10911597B2 (en) Method for operating a communication system, telecommunication apparatus and computer program product
US20040101128A1 (en) DTMF control
CN108449517A (en) Call method and device based on the more card business of No.1
CN111405131A (en) Method, system and storage medium for detecting far-end off-hook signal
CN112217934A (en) Voice recognition processing method and system in real-time communication system
CN110611731A (en) Method and device for resisting malicious call

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20090603

Termination date: 20210308