CN112351146A - Off-hook detection method, device, equipment, storage medium and telephone calling system - Google Patents

Off-hook detection method, device, equipment, storage medium and telephone calling system Download PDF

Info

Publication number
CN112351146A
CN112351146A CN202011215896.7A CN202011215896A CN112351146A CN 112351146 A CN112351146 A CN 112351146A CN 202011215896 A CN202011215896 A CN 202011215896A CN 112351146 A CN112351146 A CN 112351146A
Authority
CN
China
Prior art keywords
target text
content
counter
voice
hook
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.)
Granted
Application number
CN202011215896.7A
Other languages
Chinese (zh)
Other versions
CN112351146B (en
Inventor
邱志超
杜浦
奚海庭
何宏洋
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.)
Anhui Iflytek Zhiyue Technology Co ltd
Original Assignee
Anhui Iflytek Zhiyue Technology 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 Anhui Iflytek Zhiyue Technology Co ltd filed Critical Anhui Iflytek Zhiyue Technology Co ltd
Priority to CN202011215896.7A priority Critical patent/CN112351146B/en
Publication of CN112351146A publication Critical patent/CN112351146A/en
Application granted granted Critical
Publication of CN112351146B publication Critical patent/CN112351146B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/22—Arrangements for supervision, monitoring or testing
    • H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/42314—Systems providing special services or facilities to subscribers in private branch exchanges
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/527—Centralised call answering arrangements not requiring operator intervention
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M7/00—Arrangements for interconnection between switching centres
    • H04M7/0024—Services and arrangements where telephone services are combined with data services
    • H04M7/0042—Services and arrangements where telephone services are combined with data services where the data service is a text-based messaging service
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Computer Security & Cryptography (AREA)
  • Technology Law (AREA)
  • Telephone Function (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The application provides an off-hook detection method, an off-hook detection device, an off-hook detection apparatus, a storage medium and a telephone call system, wherein the off-hook detection method comprises the following steps: when a call is called out, whether a voice exists in a telephone line is detected; when voice exists in the telephone line, the voice is transcribed into a text which is used as a target text; judging whether the content of the target text is the content of the manual reply or not; and if the content of the target text is the content of the manual reply, judging that the called party is off-hook. The off-hook detection method provided by the application can detect whether the called party is off-hook according to the content of the voice in the telephone line.

Description

Off-hook detection method, device, equipment, storage medium and telephone calling system
Technical Field
The present application relates to the field of telephone calling technologies, and in particular, to a method, an apparatus, a device, a storage medium, and a telephone calling system for detecting an off-hook.
Background
With the increasing maturity of the artificial intelligence related technology, more and more telephone calling works (such as hotel foreground outbound confirmation, telephone return visit work and the like) are replaced by the telephone robot, and the telephone calling works are handed to the telephone robot, so that the workload of the artificial outbound can be greatly reduced, the labor cost is saved, and the work efficiency is improved.
When a telephone calling work is carried out, whether a called party is off-hook needs to be determined, only after the called party is determined to be off-hook, a telephone robot can start broadcasting a service flow, and how to determine whether the called party is off-hook is a problem which needs to be solved at present.
Disclosure of Invention
In view of the above, the present application provides an off-hook detection method, apparatus, device, storage medium and telephone call system, which are used to determine whether a called party is off-hook when a telephone call is made, and the technical solution is as follows:
an off-hook detection method comprising:
when a call is called out, whether a voice exists in a telephone line is detected;
when voice exists in the telephone line, the voice is transcribed into a text which is used as a target text;
judging whether the content of the target text is the content of the manual reply or not;
and if the content of the target text is the content of the manual reply, judging that the called party is off-hook.
Optionally, before detecting whether there is voice in the telephone line, the off-hook detection method further includes:
detecting whether a reverse polarity signal exists in the telephone line;
if the telephone line has a reverse polarity signal, determining whether the called party is off-hook according to the reverse polarity signal;
and if the telephone line has no reverse polarity signal, executing the detection to determine whether the telephone line has voice.
Optionally, after obtaining a detection result of the called party going off-hook based on the content of the target text, the off-hook detection method further includes:
playing a guiding voice, wherein the guiding voice is used for guiding a called party to reply;
and confirming the detection result of off-hook of the called party according to the content of the voice detected after the guiding voice is played.
Optionally, the determining whether the content of the target text is the content of the manual reply includes:
judging whether a counter example matched with the target text exists in a pre-established counter example library or not, wherein each counter example in the counter example library is a non-artificial reply text;
if the counter example matched with the target text does not exist in the counter example library, identifying the semantics of the target text;
and determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
Optionally, the counter example library includes a first counter example library, and a counter example in the first counter example library is a non-manual reply text capable of indicating that the called party does not go off-hook;
the judging whether the counter examples matched with the target text exist in the pre-established counter example library or not comprises the following steps:
judging whether counterexamples matched with the target text exist in the first counterexample library or not;
correspondingly, if the counter example matched with the target text does not exist in the counter example library, identifying the semantics of the target text, including:
and if the first example library does not have the example matched with the target text, identifying the semantics of the target text.
Optionally, the example library further includes a second example library, where an example in the second example library is a text obtained by transcribing the color ring;
if the first example library does not have an example matching the target text, the determining whether a pre-established example library has an example matching the target text further includes:
further judging whether a counterexample matched with the target text exists in the second counterexample library or not;
correspondingly, if the counter example matched with the target text does not exist in the counter example library, identifying the semantics of the target text, including:
and if the second counter example library does not have the counter example matched with the target text, identifying the semantics of the target text.
Optionally, after determining that there is no counter example matching the target text in the first counter example library, before determining whether there is a counter example matching the text in the second counter example library, the method further includes:
judging whether the length of the target text is greater than a preset length threshold value or not;
and if the length of the target text is not greater than the length threshold, executing the judgment of whether a counterexample matched with the text exists in the second counterexample library.
The off-hook detection method further comprises:
if the first counter-example library has the counter-example matched with the target text, determining that the call fails, and ending the off-hook detection process;
if the length of the target text is greater than the length threshold value, or a counterexample matched with the target text exists in the second counterexample library, playing detection voice to detect whether a called party is off-hook or not, and determining whether the detection duration is greater than a preset maximum detection duration or not in the detection process;
if the detection duration is longer than the maximum detection duration, determining that the call fails, and ending the off-hook detection process.
An off-hook detection device, comprising: voice detection module, voice transcription module and off-hook detection module:
the voice detection module is used for detecting whether voice exists in a telephone line when a telephone call is called;
the voice transcription module is used for transcribing the voice into a text as a target text when the voice exists in the telephone line;
and the off-hook detection module is used for determining whether the content of the target text is the content of manual reply or not, and if the content of the target text is the content of manual reply, determining that the called party is off-hook.
Optionally, the off-hook detection apparatus further includes: an off-hook confirmation module;
and the off-hook confirming module is used for playing a guiding voice and confirming the detection result of off-hook of the called party according to the content of the voice detected after the guiding voice is played, wherein the guiding voice is used for guiding the called party to reply.
Optionally, the off-hook detection module includes: the matching counter-example judging module, the semantic recognition module and the text content confirming module;
the matching counter example judging module is used for judging whether a counter example matched with the target text exists in a pre-established counter example library or not, wherein each counter example in the counter example library is a non-artificial reply text;
the semantic recognition module is used for recognizing the semantics of the target text when the matching counter example determining sub-module determines that the counter example matched with the target text does not exist in the counter example library;
and the text content confirmation module is used for determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
An off-hook detection device comprising: a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement each step of the off-hook detection method according to any one of the above descriptions.
A readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the off-hook detection method of any one of the above.
A telephone call system comprising: a telephone robot, a telephone stored program control exchange and a voice gateway;
the telephone robot is used for issuing an outbound task;
the voice gateway is used for transmitting the outbound task to the telephone stored program control exchange;
the telephone program controlled switch is used for calling a communication terminal of a called party according to the outbound task;
the telephone robot is further configured to detect whether the called party goes off-hook by using the off-hook detection method.
According to the above scheme, when a telephone call is performed, firstly, whether a voice exists in a telephone line is detected, when the voice exists in the telephone line, the voice is transcribed into a text as a target text, then, whether the content of the target text is the content of a manual reply is determined, and if the content of the target text is the content of the manual reply, a called party is determined to be off-hooked. The off-hook detection method, the device, the equipment, the storage medium and the telephone calling system can detect whether the called party is off-hook or not based on the text corresponding to the voice in the telephone line.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flow chart of an off-hook detection method according to an embodiment of the present application;
fig. 2 is another schematic flow chart of an off-hook detection method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a first implementation manner of determining whether content of a target text is content of an artificial reply in the off-hook detection method according to the embodiment of the present application;
fig. 4 is a schematic flowchart of a second implementation manner of determining whether the content of the target text is a content replied manually in the off-hook detection method according to the embodiment of the present application;
fig. 5 is a schematic flowchart of a third implementation manner of determining whether the content of the target text is the content of the manual reply in the off-hook detection method provided in the embodiment of the present application;
fig. 6 is a schematic flowchart of a fourth implementation manner of determining whether the content of the target text is the content of the manual reply in the off-hook detection method provided in the embodiment of the present application;
fig. 7 is a schematic flowchart of an embodiment of an off-hook detection method according to the present application;
fig. 8 is a schematic structural diagram of an off-hook detection apparatus according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an off-hook detection apparatus according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a telephone calling system according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The inventor discovers that: the existing off-hook detection scheme is mainly an off-hook detection scheme based on a reverse polarity signal, and the principle of the off-hook detection scheme based on the reverse polarity signal is as follows: in view of the fact that voltage reversal occurs on the telephone line at the moment when the called party goes off-hook, whether the called party goes off-hook can be determined by detecting the voltage of the telephone line.
If an off-hook detection scheme based on the reverse polarity signal is to be realized, firstly a reverse polarity signal service of a telephone PSTN line needs to be applied to an operator, and secondly, a telephone calling hardware (namely a telephone program controlled switch) needs to support the reverse polarity signal detection function. Since a business license and other qualification proofs need to be provided to an operator when applying for the service of opening the reverse polarity signal, and many telephone program controlled switches remove a reverse polarity detection function module for cost saving, in practical application scenarios, the above two conditions are usually difficult to be satisfied simultaneously, which means that an off-hook detection scheme based on the reverse polarity signal is not applicable in most practical application scenarios, that is, the off-hook detection scheme based on the reverse polarity signal has no universality.
In order to obtain an off-hook detection scheme with high universality, the inventor of the present invention has conducted intensive research, and finally provides an off-hook detection method that can be applied to any application scenario requiring off-hook detection (applicable to an application scenario that cannot satisfy the above two conditions at the same time, and also applicable to an application scenario that can satisfy the above two conditions at the same time). The off-hook detection method provided by the present application is described next by the following embodiments.
First embodiment
Referring to fig. 1, a schematic flow chart of an off-hook detection method provided in an embodiment of the present application is shown, where the method may include:
step S101: when a call is made, it is detected whether or not there is speech on the telephone line.
In this embodiment, the detection of speech in the telephone line is performed in real time.
Step S102 a: when there is voice in the telephone line, the voice is transcribed as text as a target text.
Specifically, the voice detected in the telephone line may be transcribed as a text using a voice transcription technique, the transcribed text is used as a target text, and then S103 is performed.
Step S102 b: when no voice exists in the telephone line, the detection is continued based on a preset mute processing strategy.
In practical applications, there may be a case where a voice is detected in the telephone circuit, and if this occurs, the above step S102a is executed, and of course, there may also be a case where no voice is detected in the telephone circuit, and if no voice is detected in the telephone circuit, the following mute processing strategy may be adopted for processing: and playing the guide voice to guide the user to speak, meanwhile, judging whether the waiting time (the waiting time refers to the time for waiting the user to speak after the guide voice is played) reaches the preset maximum waiting time, if the waiting time reaches the preset maximum waiting time, determining that the calling fails, ending the off-hook detection process, and if the waiting time does not reach the preset maximum waiting time, continuously detecting whether the voice exists in the line.
Alternatively, in order to enable the off-hook detection process to be performed normally, the above-mentioned "no voice is detected in the telephone line" means that no voice is detected within a preset time period after the calling operation is performed.
Step S103: and judging whether the content of the target text is the content of the manual reply.
Specifically, the process of determining whether the content of the target text is the content of the manual reply may include: determining whether a counter example matched with the target text exists in a pre-established counter example library, if the counter example matched with the target text exists in the counter example library, determining that the content of the target text is the non-manually replied content, if the counter example matched with the target text does not exist in the counter example library, determining that the content of the target text may be the manually replied content, at the moment, further identifying the semantics of the target text, and determining whether the content of the target text is the manually replied content according to the semantics of the target text.
It should be noted that each counter example in the counter example library is a non-manual reply text.
Step S104 a: and if the content of the target text is the content replied manually, determining that the called party is off-hook.
It should be noted that the term "content of manual reply" mentioned in this application refers to the content of real reply, and it should be noted that "called party goes off-hook" mentioned in this application refers to a state, not to an action, that is, the off-hook detection method of this application essentially detects whether the called party is in an off-hook state, not whether the called party has taken an off-hook action.
Step S104 b: if the content of the target text is the content of the manual reply, ending the off-hook detection process, or continuing to detect based on a preset detection strategy.
Specifically, if the content of the target text is a non-manual reply text which can indicate that the called party cannot be off-hooked, determining that the call fails, and ending the off-hook detection process, if the content of the target text is not the non-manual reply text which can indicate that the called party cannot be off-hooked, playing a detection voice to continuously detect whether the called party is off-hooked, more specifically, after playing the detection voice, detecting whether the voice appears in a telephone line, meanwhile, judging whether the waiting duration is greater than a preset maximum waiting duration, if the waiting duration is greater than the preset maximum waiting duration, determining that the call fails, ending the off-hook detection process, otherwise, continuously detecting.
The off-hook detection method provided by the embodiment of the application detects whether voice exists in a telephone line or not when a telephone call is carried out, when the voice exists in the telephone line, the voice is transcribed into a text to be used as a target text, then whether the content of the target text is the content of manual response or not is determined, and if the content of the target text is the content of manual response, the called party is determined to be off-hook. The off-hook detection method provided by the embodiment of the application can detect whether the called party is off-hook or not based on the text corresponding to the voice in the telephone line.
Second embodiment
In order to obtain a higher off-hook detection accuracy, the present application provides another off-hook detection method, please refer to fig. 2, which shows a flow diagram of the off-hook detection method, and the off-hook detection method includes the following steps in addition to steps S101 to S104 in the above embodiment:
step S105: the detection result that the called party obtained via step S104a is off-hook is confirmed.
Specifically, the process of confirming that the detection result of the called party being off-hook obtained through step S104a may include: and playing the guide voice, and confirming the detection result of off-hook of the called party according to the content of the voice detected after the guide voice is played. Wherein the guiding voice is used for guiding the called party to reply.
More specifically, the process of confirming the detection result of the called party going off-hook according to the content of the voice detected after the guiding voice is played comprises: judging whether the content of the voice detected after the guiding voice is played is the content of the manual reply or not; and if the content of the voice detected after the guiding voice is played is judged to be the content of the manual reply, confirming that the called party is actually off-hook.
The process of determining whether the content of the voice detected after the guidance voice is played is the content replied manually may include: the method includes the steps of transcribing voice detected after guide voice playing into a text, recognizing the semantic meaning of the text, judging whether the content of the voice detected after the guide voice playing is the content of manual reply or not according to the semantic meaning of the text, more specifically, if the text is the text with definite meaning, determining that the content of the voice detected after the guide voice playing is the content of manual reply, and if the text is the text without definite meaning, determining that the content of the voice detected after the guide voice playing is the content of non-manual reply. Exemplary, "hello," "on," "who you find" and the like are text of definite significance.
As mentioned above, when it is determined that the content of the voice detected after the guidance voice is played is the content of the manual reply, it may be determined that the called party is actually off-hooked, and in practical applications, there may be a case where it is determined that the content of the voice detected after the guidance voice is played is the content of the non-manual reply, or there may be a case where it is not determined that the content of the voice detected after the guidance voice is played is the content of the manual reply or the content of the non-manual reply, and for these two cases, the present embodiment provides the following strategies:
if the content of the voice detected after the guiding voice is played is judged to be the content of the non-manual reply, the detection is continued based on a preset first detection strategy, and if the content of the voice detected after the guiding voice is played cannot be judged to be the content of the manual reply or the content of the non-manual reply, the detection is carried out based on a preset second detection strategy. Specifically, the process of detecting based on the preset first detection strategy is as follows: and playing detection voice capable of guiding the called party to reply, after the detection voice is played, carrying out voice detection, meanwhile, judging whether the time length for waiting the called party to reply is greater than the preset maximum waiting time length, if so, determining that the calling fails, ending the off-hook detection process, and if not, continuing the detection. The process of detecting based on the preset second detection strategy is similar to the process of detecting based on the preset first detection strategy, except that the played detection voice is greeting voice.
The off-hook detection method provided by the embodiment of the application detects whether a voice exists in a telephone line or not when a telephone call is carried out, when the voice exists in the telephone line, the voice is transcribed into a text to be used as a target text, then whether the content of the target text is the content of manual reply or not is determined, if the content of the target text is the content of manual reply, the off-hook of a called party is determined, and after the off-hook of the called party is determined, the detection result of the off-hook of the called party is confirmed in order to obtain a more accurate detection result. The off-hook detection method provided by the embodiment of the application can detect whether the called party is off-hook according to the content of the voice in the telephone line, and has higher detection accuracy.
Third embodiment
This embodiment is similar to the "step S103: and judging whether the content of the target text is the content of the manual reply or not.
There are various implementation manners for determining whether the content of the target text is the content of the manual reply, and this embodiment provides the following four optional implementation manners:
referring to fig. 3, a flow chart of a first implementation manner is shown, which may include:
step S301: and judging whether counterexamples matched with the target text exist in the first counterexample library.
Wherein each counter example in the first counter example library is a non-manual reply text capable of indicating that the called party does not go off-hook. Illustratively, the non-human reply text that can indicate that the called party is not off-hook is "out of service area device", "user has powered off", etc.
Specifically, the process of determining whether a counterexample matching the target text exists in the first counterexample library may include: calculating the similarity between each counterexample in the first reaction library and the target text to obtain the similarity corresponding to each counterexample in the first reaction library, judging whether the maximum similarity in the obtained similarities is larger than a preset similarity threshold, if the maximum similarity is larger than the preset similarity threshold, judging that the counterexample matched with the target text exists in the first reaction library (the counterexample matched with the target text is the counterexample corresponding to the maximum similarity), and otherwise, judging that the counterexample matched with the target text does not exist in the first reaction library.
Step S302: and if the counter example matched with the target text does not exist in the first counter example library, identifying the semantics of the target text.
And on the basis, the semantics of the target text are identified, and whether the content of the target text is the content of the artificial reply is further determined based on the semantics of the target text.
It should be noted that, if a counterexample matching the target text exists in the first counterexample library, it is determined that the content of the target text is the non-manual reply text.
Step S303: and determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
Considering that the content replied by the real person usually has a definite meaning, such as "hello", "is", "who you find", and the like, the embodiment determines whether the target text has a definite meaning according to the semantics of the target text, determines that the content of the target text is the content replied by the human if the target text has the definite meaning, and determines that the content of the target text is the content replied by the non-human if the target text does not have the definite meaning.
In view of the fact that the semantic recognition efficiency of a short text is high, and the first sentence spoken after the called party goes off-hook is generally short, in order to improve the efficiency of determining whether the content of the target text is the content of the manual reply, this embodiment proposes a second implementation manner on the basis of the first implementation manner, please refer to fig. 4, which shows a flowchart of the second implementation manner, and may include:
step S401: and judging whether counterexamples matched with the target text exist in the first counterexample library.
Wherein each counter example in the first counter example library is a non-manual reply text capable of indicating that the called party does not go off-hook.
Step S402: and if the first counter library does not have a counter example matched with the target text, judging whether the length of the target text is greater than a preset length threshold value.
Specifically, the length of the target text may be represented by the number of words of the target text, and based on this, the process of determining whether the length of the target text is greater than the preset length threshold includes: it is determined whether the number of words of the target text is greater than a preset word number threshold (e.g., 30 words).
Step S403: and if the length of the target text is not greater than a preset length threshold value, identifying the semantics of the target text.
If the length of the target text is not greater than the preset length threshold, the target text is short, and therefore the content of the target text can be determined to be the content of the manual reply.
It should be noted that, if the length of the target text is greater than the preset length threshold, the target text is longer, and it can be determined that the target text is a text that is not manually replied.
Step S404: and judging whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
The first implementation manner and the second implementation manner are more suitable for the case that the called party does not open the color ring back tone service, and for the case that the called party opens the color ring back tone service, the embodiment provides the following implementation manners:
referring to fig. 5, a flow chart of a third implementation manner is shown, which may include:
step S501: and judging whether counterexamples matched with the target text exist in the first counterexample library.
Wherein each counter example in the first counter example library is a non-manual reply text capable of indicating that the called party does not go off-hook.
Step S502: if the counter example matched with the target text does not exist in the first counter example library, whether a counter example matched with the target text exists in the second counter example library is further judged.
It should be noted that if a counterexample matching the target text exists in the first reverse library, the content of the target text may be directly determined to be the content of the non-manual reply, and if the counterexample matching the target text does not exist in the first reverse library, it is further determined whether a counterexample matching the target text exists in the second reverse library.
Each counterexample in the second counterexample library is a text obtained by transcribing a color ring. In this embodiment, all the ring back tones can be collected, each ring back tone is transcribed into a text, and all the texts obtained by transcription form a second example library.
Step S503: and if the second counter example library does not have the counter example matched with the target text, identifying the semantics of the target text.
It should be noted that if the counter example matching the target text exists in the second counter example library, the content of the target text may be directly determined to be the content of the non-manual reply, and if the counter example matching the target text does not exist in the second counter example library, the content of the target text may be the content of the manual reply, and at this time, the semantics of the target text is further identified.
Step S504: and determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
In order to improve the efficiency of determining whether the content of the target text is the content of the manual reply, the present embodiment provides a fourth implementation manner based on the third implementation manner, please refer to fig. 6, which shows a flowchart of the fourth implementation manner, and the flowchart may include:
step S601: it is determined whether there are counterexamples in the first counter library that match the target text.
Step S602: and if the counter example matched with the target text does not exist in the first counter example library, determining whether the length of the target text is greater than a preset length threshold value.
It should be noted that, if there is a counter example matching the target text in the first counter example library, the content of the target text may be directly determined as the content of the non-artificial reply, and if there is no counter example matching the target text in the first counter example library, the determination is further performed according to the length of the target text.
Step S603: and if the length of the target text is not greater than the length threshold value, further determining whether counterexamples matched with the target text exist in the second counter library.
If the length of the target text is larger than the preset length threshold, the target text is longer, the content of the target text can be determined to be the non-manually replied content, if the length of the target text is not larger than the preset length threshold, the target text is shorter, the content of the target text can be determined to be the manually replied content, and at the moment, the judgment is further carried out based on a second counter example library.
Step S604: and if the second counter example library does not have the counter example matched with the target text, identifying the semantics of the target text.
If the second example library has the example matching the target text, the content of the target text can be directly judged to be the non-manually replied content, and if the second example library does not have the example matching the target text, the content of the target text is possibly the manually replied content, and at this time, the semantic judgment is further based on the target text.
Step S605: and determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
Fourth embodiment
On the basis of the first to third embodiments, this embodiment provides an embodiment of an off-hook detection method, please refer to fig. 7, which shows a flowchart of the embodiment, and the method may include:
step S701: detecting whether a reverse polarity signal exists in the telephone line, if no reverse polarity signal exists in the telephone line, executing step S702, and if the reverse polarity signal exists in the telephone line, determining whether the called party is off-hook according to the reverse polarity signal.
The process of determining whether the called party goes off-hook according to the reverse polarity signal is the prior art, and the details of this embodiment are not described herein.
Step S702: detecting whether the telephone line has voice, if so, executing step S703, and if not, detecting based on a preset mute processing strategy.
For a specific process of performing detection based on a preset muting strategy, reference may be made to the above embodiments, which are not described herein again.
Step S703: and judging whether the first reverse library has a counterexample matched with the target text, if the first reverse library does not have the counterexample matched with the target text, executing the step S704, and if the first reverse library has the counterexample matched with the target text, determining that the call fails and ending the off-hook detection process.
Each counter example in the first counter example library is a non-manual reply text which can indicate that a called party cannot be off-hooked, if a counter example which is matched with the target text exists in the first counter example library, the target text is the non-manual reply text which can indicate that the called party cannot be off-hooked, at this time, it is determined that a user cannot be off-hooked, a call is failed, an off-hook detection process is ended, if the counter example which is matched with the target text does not exist in the first counter example library, the target text is possibly a manual reply text, and at this time, the target text is continuously judged.
Step S704: and judging whether the length of the target text is greater than a preset length threshold, if the length of the target text is not greater than the preset length threshold, executing the step S705, if the length of the target text is greater than the preset length threshold, determining that the target text is a non-manually replied text, and continuing to detect based on a preset first detection strategy.
The length of the target text is greater than the preset length threshold, which indicates that the target text is a long text, and considering that the first sentence spoken after the called party goes off the phone is generally short, in this embodiment, when the length of the target text is greater than the preset length threshold, it is determined that the target text is a non-manual reply text, and if the length of the target text is not greater than the preset length threshold, it indicates that the target text is a short text, and at this time, the target text is continuously distinguished.
Step S705: and judging whether a counter example matched with the target text exists in the second counter example library, if the counter example matched with the target text does not exist in the second counter example library, executing the step S706, if the counter example matched with the target text exists in the second counter example library, determining that the target text is a non-artificial reply text, and continuously detecting based on a preset first detection strategy.
Each counterexample in the second feedback library is a text obtained by transcribing a color ring, if a counterexample matching with the target text exists in the second feedback library, it is indicated that the detected voice is the color ring, the target text is the content of the color ring, that is, the target text is the non-artificial reply text, and if no counterexample matching with the target text exists in the second feedback library, it is indicated that the content of the target text may be the content of the artificial reply, and at this time, further confirmation is needed.
Step S706: semantics of the target text are identified.
The semantic recognition can be performed on the target text by adopting the existing semantic recognition technology.
Step S707: and judging whether the called party is off-hook according to the semantic meaning of the target text, and if the called party is judged to be off-hook according to the semantic meaning of the target text, executing the step S708.
Specifically, whether the content of the target text is the content of the manual reply is judged according to the semantics of the target text, if the content of the target text is the content of the manual reply, the called party can be preliminarily judged to be off-hooked, if the content of the target text is the content of the non-manual reply, the called party is judged not to be off-hooked, at this moment, a guide voice can be played to guide the called party to reply, and after the guide voice is played, if the voice is detected, whether the called party is off-hooked is judged according to whether the content of the detected voice has a clear meaning.
Step S708: the detection result that the called party is off-hook is confirmed.
Specifically, the process of confirming the detection result of the called party going off-hook includes: and playing a guide voice to guide the called party to reply, transcribing the voice detected after playing the guide voice into a text, determining whether the content of the text is the content of manual reply, if so, confirming that the called party is off-hook, if the content of the text is the content of non-manual reply, continuing detection based on a preset first detection strategy, and if the content of the text cannot be determined to be the content of manual reply or the content of non-manual reply, continuing detection based on a preset second detection strategy. The process of performing detection based on the preset first detection strategy and the process of performing detection based on the preset second detection strategy may refer to the above embodiments, which are not described herein again.
According to the off-hook detection method provided by the embodiment of the application, when a reverse polarity signal exists in a telephone line, whether a called party is off-hook or not can be determined according to the reverse polarity signal, when the reverse polarity signal does not exist in the telephone line, whether the called party is off-hook or not can be determined according to the content of voice detected in the telephone line, and when the called party is determined to be off-hook or not according to the content of the voice detected in the telephone line, a judgment strategy based on a reverse case base, a judgment strategy based on text length, a judgment strategy based on text semantics and a confirmation strategy based on a guide word are adopted, and whether the called party is off-hook or not can be accurately judged.
Fifth embodiment
The embodiments of the present application further provide an off-hook detection apparatus, which is described below, and the off-hook detection apparatus described below and the off-hook detection method described above may be referred to in correspondence with each other.
Referring to fig. 8, a schematic structural diagram of an off-hook detection apparatus provided in this embodiment is shown, which may include: voice detection module 801, voice transcription module 802, and off-hook detection module 803.
The voice detection module 801 is configured to detect whether there is voice in a telephone line when a call is placed outside.
A voice transcription module 802, configured to transcribe, when there is voice in the telephone line, the voice into a text as a target text.
An off-hook detection module 803, configured to determine whether the content of the target text is a content replied manually, and determine that the called party is off-hook if the content of the target text is the content replied manually.
Optionally, the off-hook detection apparatus provided in this embodiment may further include: the device comprises a reverse polarity signal detection module and an off-hook judgment module.
A reverse polarity signal detection module, configured to detect whether there is a reverse polarity signal in the telephone line before the voice detection module 801 detects whether there is a voice in the telephone line.
And the off-hook judging module is used for determining whether the called party is off-hook according to the reverse polarity signal when the reverse polarity signal detecting module detects that the reverse polarity signal exists in the telephone line.
The voice detection module 801 is specifically configured to detect whether there is a voice in the telephone line when there is no reverse polarity signal in the telephone line.
Optionally, the off-hook detection apparatus provided in this embodiment may further include: and a detection result confirmation module.
And the detection result confirmation module is used for playing a guide voice and confirming the detection result of off-hook of the called party according to the content of the voice detected after the guide voice is played, wherein the guide voice is used for guiding the called party to reply.
Optionally, the off-hook detection module includes: a matching counter-example judging module, a semantic recognition module and a text content confirming module.
The matching counter example judging module is used for judging whether a counter example matched with the target text exists in a pre-established counter example library, wherein each counter example in the counter example library is a non-artificial reply text.
The semantic recognition module is configured to recognize the semantic meaning of the target text when the matching counter example determination sub-module determines that there is no counter example matching the target text in the counter example library.
And the text content confirmation module is used for determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
Optionally, the counter-example library includes a first counter-example library, and the counter-example in the first counter-example library is a non-manual reply text capable of indicating that the called party does not go off-hook.
The matching counter example judging module is specifically used for judging whether a counter example matched with the target text exists in the first counter example library or not; correspondingly, the semantic recognition module is specifically configured to recognize the semantics of the target text when no counter-example matching the target text exists in the first counter-example library.
Optionally, the counter-example library further includes a second counter-example library, and the counter-example in the second counter-example library is a text obtained by transcribing the color ring.
The matching counter-example judging module is further configured to, when it is determined that the counter-example matching the target text does not exist in the first counter-example library, further judge whether the counter-example matching the target text exists in the second counter-example library; correspondingly, the semantic recognition module is specifically configured to recognize the semantics of the target text when it is determined that the second counter example library does not have a counter example matching the target text.
Optionally, the off-hook detection module 80 further includes: and a text length judging module.
The text length judging module is used for judging whether the length of the target text is greater than a preset length threshold value or not before judging whether the counter example matched with the text exists in the second counter example library or not after the matching counter example judging module judges that the counter example matched with the target text does not exist in the first counter example library; correspondingly, when the length of the target text is not greater than the length threshold, the matching counter-example judging module executes the judgment to determine whether a counter example matched with the text exists in the second counter-example library.
Optionally, the off-hook detection module 803 is further configured to determine that the call fails when a counter example matching the target text exists in the first counter example library, and end the off-hook detection process; and when the length of the target text is greater than the length threshold value or a counter example matched with the target text exists in the second counter example library, playing detection voice to detect whether a called party is off-hook or not, determining whether the detection duration is greater than a preset maximum detection duration or not in the detection process, and if the detection duration is greater than the maximum detection duration, ending an off-hook detection process and determining that the call fails.
The off-hook detection device provided by the embodiment of the application can accurately judge whether the called party is off-hook.
Sixth embodiment
An off-hook detection device is further provided in the embodiment of the present application, please refer to fig. 9, which shows a schematic structural diagram of the off-hook detection, where the off-hook detection may include: at least one processor 901, at least one communication interface 902, at least one memory 903 and at least one communication bus 904;
in the embodiment of the present application, the number of the processor 901, the communication interface 902, the memory 903, and the communication bus 904 is at least one, and the processor 901, the communication interface 902, and the memory 903 complete communication with each other through the communication bus 904;
processor 901 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 903 may include a high-speed RAM memory, a non-volatile memory (non-volatile memory), and the like, such as at least one disk memory;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
when a call is called out, whether a voice exists in a telephone line is detected;
when voice exists in the telephone line, the voice is transcribed into a text which is used as a target text;
judging whether the content of the target text is the content of the manual reply or not;
and if the content of the target text is the content of the manual reply, judging that the called party is off-hook.
Alternatively, the detailed function and the extended function of the program may be as described above.
Seventh embodiment
Embodiments of the present application further provide a readable storage medium, where a program suitable for being executed by a processor may be stored, where the program is configured to:
when a call is called out, whether a voice exists in a telephone line is detected;
when voice exists in the telephone line, the voice is transcribed into a text which is used as a target text;
judging whether the content of the target text is the content of the manual reply or not;
and if the content of the target text is the content of the manual reply, judging that the called party is off-hook.
Alternatively, the detailed function and the extended function of the program may be as described above.
Eighth embodiment
An embodiment of the present application further provides a telephone calling system, please refer to fig. 10, which shows a schematic structural diagram of the system, and the system may include: a telephone robot 1001, a voice gateway 1002, and a telephone program controlled switch 1003.
And the telephone robot 1001 is used for issuing an outbound task.
Specifically, the telephone robot may establish a network connection with the voice gateway through the communication network, and issue the call task to the voice gateway 1002 through the communication network.
A voice gateway 1002 for transmitting outbound tasks to the telephony private branch exchange 1003.
The telephone stored program controlled exchange 1003 is used for calling the communication terminal of the called party according to the outbound task.
The telephone robot 1001 is further configured to detect whether the called party goes off-hook by using the off-hook detection method provided in the above embodiment.
The telephone robot 1001 is further configured to start broadcasting the service flow when detecting that the called party is off-hook.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (12)

1. An off-hook detection method, comprising:
when a call is called out, whether a voice exists in a telephone line is detected;
when voice exists in the telephone line, the voice is transcribed into a text which is used as a target text;
judging whether the content of the target text is the content of the manual reply or not;
and if the content of the target text is the content of the manual reply, judging that the called party is off-hook.
2. An off-hook detection method according to claim 1, before detecting whether there is voice in said telephone line, further comprising:
detecting whether a reverse polarity signal exists in the telephone line;
if the telephone line has a reverse polarity signal, determining whether the called party is off-hook according to the reverse polarity signal;
and if the telephone line has no reverse polarity signal, executing the detection to determine whether the telephone line has voice.
3. An off-hook detection method according to claim 1, after obtaining a detection result that a called party is off-hook based on the content of the target text, further comprising:
playing a guiding voice, wherein the guiding voice is used for guiding a called party to reply;
and confirming the detection result of off-hook of the called party according to the content of the voice detected after the guiding voice is played.
4. An off-hook detection method according to claim 1, wherein the determining whether the content of the target text is a content of a manual reply includes:
judging whether a counter example matched with the target text exists in a pre-established counter example library or not, wherein each counter example in the counter example library is a non-artificial reply text;
if the counter example matched with the target text does not exist in the counter example library, identifying the semantics of the target text;
and determining whether the content of the target text is the content of the manual reply or not according to the semantic meaning of the target text.
5. An off-hook detection method according to claim 4, characterized in that the counter-example library comprises a first counter-example library, and counter-examples in the first counter-example library are non-manual reply texts capable of indicating that the called party does not go off-hook;
the judging whether the counter examples matched with the target text exist in the pre-established counter example library or not comprises the following steps:
judging whether counterexamples matched with the target text exist in the first counterexample library or not;
correspondingly, if the counter example matched with the target text does not exist in the counter example library, identifying the semantics of the target text, including:
and if the first example library does not have the example matched with the target text, identifying the semantics of the target text.
6. An off-hook detection method according to claim 5, characterized in that the counter-instance library further comprises a second counter-instance library, and the counter-instance in the second counter-instance library is a text obtained by transcribing the color ring;
if the first example library does not have an example matching the target text, the determining whether a pre-established example library has an example matching the target text further includes:
further judging whether a counterexample matched with the target text exists in the second counterexample library or not;
correspondingly, if the counter example matched with the target text does not exist in the counter example library, identifying the semantics of the target text, including:
and if the second counter example library does not have the counter example matched with the target text, identifying the semantics of the target text.
7. An off-hook detection method according to claim 6, wherein after determining that there is no counter matching the target text in the first counter library, before determining whether there is a counter matching the text in the second counter library, further comprising:
judging whether the length of the target text is greater than a preset length threshold value or not;
and if the length of the target text is not greater than the length threshold, executing the judgment of whether a counterexample matched with the text exists in the second counterexample library.
8. An off-hook detection method according to claim 7, characterized by further comprising:
if the first counter-example library has the counter-example matched with the target text, determining that the call fails, and ending the off-hook detection process;
if the length of the target text is greater than the length threshold value, or a counterexample matched with the target text exists in the second counterexample library, playing detection voice to detect whether a called party is off-hook or not, and determining whether the detection duration is greater than a preset maximum detection duration or not in the detection process;
if the detection duration is longer than the maximum detection duration, determining that the call fails, and ending the off-hook detection process.
9. An off-hook detection device, comprising: voice detection module, voice transcription module and off-hook detection module:
the voice detection module is used for detecting whether voice exists in a telephone line when a telephone call is called;
the voice transcription module is used for transcribing the voice into a text as a target text when the voice exists in the telephone line;
and the off-hook detection module is used for determining whether the content of the target text is the content of manual reply or not, and if the content of the target text is the content of manual reply, determining that the called party is off-hook.
10. An off-hook detection device, characterized by comprising: a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the off-hook detection method according to any one of claims 1 to 8.
11. A readable storage medium having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the off-hook detection method according to any one of claims 1 to 8.
12. A telephone call system, comprising: a telephone robot, a telephone stored program control exchange and a voice gateway;
the telephone robot is used for issuing an outbound task;
the voice gateway is used for transmitting the outbound task to the telephone stored program control exchange;
the telephone program controlled switch is used for calling a communication terminal of a called party according to the outbound task;
the telephone robot is also used for detecting whether the called party is off-hook by adopting the off-hook detection method of any one of claims 1-8.
CN202011215896.7A 2020-11-04 2020-11-04 Off-hook detection method, device, equipment, storage medium and telephone calling system Active CN112351146B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011215896.7A CN112351146B (en) 2020-11-04 2020-11-04 Off-hook detection method, device, equipment, storage medium and telephone calling system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011215896.7A CN112351146B (en) 2020-11-04 2020-11-04 Off-hook detection method, device, equipment, storage medium and telephone calling system

Publications (2)

Publication Number Publication Date
CN112351146A true CN112351146A (en) 2021-02-09
CN112351146B CN112351146B (en) 2022-05-31

Family

ID=74356351

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011215896.7A Active CN112351146B (en) 2020-11-04 2020-11-04 Off-hook detection method, device, equipment, storage medium and telephone calling system

Country Status (1)

Country Link
CN (1) CN112351146B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060221943A1 (en) * 2005-03-31 2006-10-05 Aborn Justin A Connecting a packet-based call to multiple devices
CN2938618Y (en) * 2006-07-24 2007-08-22 东莞方正数码通讯有限公司 Parallel operation off-hook detection, calling control signal detection and reverse polarity detection circuit
CN101662544A (en) * 2008-08-26 2010-03-03 华为技术有限公司 Method, device and system for external-call processing
CN103428372A (en) * 2012-05-16 2013-12-04 中国联合网络通信集团有限公司 Method and device for detecting phone off-hook
CN105245352A (en) * 2015-09-08 2016-01-13 烽火通信科技股份有限公司 Intelligent public telephone realization system and method based on SIP (Session Initiation Protocol) voice home gateway
US10063691B1 (en) * 2016-06-30 2018-08-28 Sorenson Ip Holdings, Llc Detecting dial tone on a telephone line
CN109309763A (en) * 2017-07-26 2019-02-05 深圳市东进银通电子有限公司 A kind of outgoing call detection method and system based on vocal print
CN109714491A (en) * 2019-02-26 2019-05-03 上海凯岸信息科技有限公司 Intelligent sound outgoing call detection system based on voice mail
CN210694073U (en) * 2019-11-08 2020-06-05 广州鲁邦通物联网科技有限公司 Called detection and calling ringing circuit of level trigger interphone
CN111405131A (en) * 2020-03-30 2020-07-10 深圳震有科技股份有限公司 Method, system and storage medium for detecting far-end off-hook signal

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060221943A1 (en) * 2005-03-31 2006-10-05 Aborn Justin A Connecting a packet-based call to multiple devices
CN2938618Y (en) * 2006-07-24 2007-08-22 东莞方正数码通讯有限公司 Parallel operation off-hook detection, calling control signal detection and reverse polarity detection circuit
CN101662544A (en) * 2008-08-26 2010-03-03 华为技术有限公司 Method, device and system for external-call processing
CN103428372A (en) * 2012-05-16 2013-12-04 中国联合网络通信集团有限公司 Method and device for detecting phone off-hook
CN105245352A (en) * 2015-09-08 2016-01-13 烽火通信科技股份有限公司 Intelligent public telephone realization system and method based on SIP (Session Initiation Protocol) voice home gateway
US10063691B1 (en) * 2016-06-30 2018-08-28 Sorenson Ip Holdings, Llc Detecting dial tone on a telephone line
CN109309763A (en) * 2017-07-26 2019-02-05 深圳市东进银通电子有限公司 A kind of outgoing call detection method and system based on vocal print
CN109714491A (en) * 2019-02-26 2019-05-03 上海凯岸信息科技有限公司 Intelligent sound outgoing call detection system based on voice mail
CN210694073U (en) * 2019-11-08 2020-06-05 广州鲁邦通物联网科技有限公司 Called detection and calling ringing circuit of level trigger interphone
CN111405131A (en) * 2020-03-30 2020-07-10 深圳震有科技股份有限公司 Method, system and storage medium for detecting far-end off-hook signal

Also Published As

Publication number Publication date
CN112351146B (en) 2022-05-31

Similar Documents

Publication Publication Date Title
US8099287B2 (en) Automatically providing a user with substitutes for potentially ambiguous user-defined speech commands
CN107038220B (en) Method, intelligent robot and system for generating memorandum
US9571638B1 (en) Segment-based queueing for audio captioning
US6941266B1 (en) Method and system for predicting problematic dialog situations in a task classification system
US20020196911A1 (en) Methods and apparatus for conversational name dialing systems
US7590224B1 (en) Automated task classification system
CA2571009A1 (en) Methods and systems for touch-free call origination
US20160036969A1 (en) Computer-based streaming voice data contact information extraction
KR20190049260A (en) Device and method for recognizing voice of vehicle
CN102984666A (en) Contact list speech information processing method and system during communication
KR20080024752A (en) Dialog management apparatus and method for chatting agent
US20050149337A1 (en) Automatic speech recognition to control integrated communication devices
CN103856602A (en) System and method for duplicating call
CN103680505A (en) Voice recognition method and voice recognition system
CN105323392A (en) Method and apparatus for quickly entering IVR menu
CN114155839A (en) Voice endpoint detection method, device, equipment and storage medium
CN112351146B (en) Off-hook detection method, device, equipment, storage medium and telephone calling system
CN105007365B (en) A kind of extension number dialing method and device
JP3933813B2 (en) Spoken dialogue device
CN107645613A (en) The method and apparatus of service diverting search
CN203278958U (en) Conversation transcription system
CN112530436A (en) Method, system, device and storage medium for identifying communication traffic state
JP2019139280A (en) Text analyzer, text analysis method and text analysis program
JP2006113439A (en) Speech automatic responding apparatus and program
CN113422875B (en) Voice seat response method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant