CN112291421A - Single-pass detection method and device based on voice communication, storage medium and electronic equipment - Google Patents
Single-pass detection method and device based on voice communication, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112291421A CN112291421A CN201910673134.2A CN201910673134A CN112291421A CN 112291421 A CN112291421 A CN 112291421A CN 201910673134 A CN201910673134 A CN 201910673134A CN 112291421 A CN112291421 A CN 112291421A
- Authority
- CN
- China
- Prior art keywords
- code stream
- voice
- calling
- called
- pass
- 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
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2236—Quality of speech transmission monitoring
Abstract
The embodiment of the application provides a one-way detection method and device based on voice communication, a storage medium and electronic equipment, and relates to the field of communication. By collecting the speech code stream transmitted in the communication network; separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream; respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame; and when the number of the continuous change rates smaller than the preset first threshold in the first change rates or the second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end. The single-pass can be determined by directly analyzing the voice code stream, a large amount of coding and decoding calculation and voice analysis calculation are not needed, the calculation resources are saved, and the processing efficiency is high.
Description
Technical Field
The present application relates to the field of communications, and in particular, to a method and an apparatus for detecting a single-pass based on voice communication, a storage medium, and an electronic device.
Background
In daily life, remote voice interaction is usually performed through a telephone, and the specific mode is that a calling terminal converts voice into a voice code stream, the voice code stream is transmitted to a called terminal through a series of communication network elements in a communication network, and the voice code stream is restored into voice for playing by the called terminal. In the transmission process, a single pass phenomenon occurs in the transmission of the voice code stream often due to the fault of the communication equipment in the communication network element. I.e. the calling or called end is in a continuous pure silent state. In order to maintain good voice communication, it is therefore necessary to periodically detect the status of voice interaction (e.g., placing a call).
In the traditional technology, when the single-pass phenomenon in voice interaction is detected, original voice is restored by decoding a voice code stream, and the original voice is analyzed in batches to judge whether the single-pass phenomenon exists. However, the above method needs to involve a large amount of coding and decoding calculations and speech analysis calculations, and needs to consume a lot of computing resources, and has low processing efficiency, so that the method cannot be widely popularized in practical applications.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for detecting a single-pass based on voice communication, a storage medium, and an electronic device, so as to improve the above-mentioned problems.
In order to solve the above technical problem, the embodiment of the present application is implemented as follows:
in a first aspect, an embodiment of the present application provides a single-pass detection method based on voice communication, including:
collecting voice code stream transmitted in a communication network;
separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream;
respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame;
and when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end.
Optionally, after determining that the single-pass phenomenon occurs at the calling terminal or the called terminal, the method further includes:
dividing a plurality of first change rates corresponding to a calling end or a plurality of second change rates corresponding to a called end, which are not determined to have a single-pass phenomenon, into a plurality of sequence segments;
determining a correlation coefficient of each sequence segment of the plurality of sequence segments with the rest sequence segments, and generating a correlation coefficient sequence;
and when the number of the correlation coefficients in the correlation coefficient sequence, which are larger than the preset coefficient threshold value, exceeds a second threshold value, generating a prompt for representing the successful verification of the occurrence of the single-pass phenomenon.
Optionally, after determining that the single-pass phenomenon occurs at the calling terminal or the called terminal, the method further includes:
recording the starting time and the ending time of the continuous change rate;
and a plurality of first change rates corresponding to the calling terminal or a plurality of second change rates corresponding to the called terminal, which are not determined to have the single-pass phenomenon, are generated in the starting time and the ending time.
Optionally, the analyzing and processing the calling code stream and the called code stream respectively includes:
equation of basis
Respectively analyzing and processing the calling code stream and the called code stream, wherein len (v)j) For the length of the current data frame, len (V)j-1) Is the length of the data frame preceding the current data frame, M being Vj-1And vjIn which the data contents of the corresponding positions are differentThe number of bytes, Cj is the first rate of change or the second rate of change.
Optionally, the determining the correlation coefficient of each sequence segment of the plurality of sequence segments with the remaining sequence segments comprises:
equation of basis
Determining a correlation coefficient of each sequence segment of the plurality of sequence segments with the rest of the sequence segments, wherein X, Y is two sequence segments of which the correlation coefficients with each other are to be determined, and r (X, Y) is the correlation coefficient.
Optionally, after determining that the single-pass phenomenon occurs at the calling terminal or the called terminal, the method further includes:
acquiring a communication equipment list related to a calling IP address and a called IP address in a calling code stream or a called code stream with a single-pass phenomenon within a preset time length;
determining a single-pass correlation coefficient of each communication device according to the total times of the single-pass phenomena and the times of the single-pass phenomena when each communication device in the communication device list bears the voice code stream;
and sorting the single-pass correlation coefficients in a descending order, and determining the communication equipment positioned at the top N as fault equipment.
Optionally, the determining the single-pass correlation coefficient of each communication device according to the total number of times of occurrence of the single-pass phenomenon and the number of times of occurrence of the single-pass phenomenon when each communication device bears the voice code stream includes:
equation of basis
Determining a single-pass correlation coefficient for each of the communication devices, wherein Ei,jIs a one-pass correlation coefficient, Qi,jThe number of times of single pass phenomenon of the jth communication equipment in the ith type network element within the preset time length is Si,jAnd the number of times of single pass phenomenon of the ith network element in the preset time length is obtained.
In a second aspect, an embodiment of the present application provides a single-pass detection apparatus based on voice communication, including:
an information acquisition unit configured to acquire a voice code stream transmitted in a communication network;
a code stream separation unit configured to separate the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream;
the change rate generation unit is configured to analyze and process the calling code stream and the called code stream respectively so as to generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame respectively;
and the single-pass determining unit is configured to determine that a single-pass phenomenon occurs at the calling terminal or the called terminal when the number of continuous change rates smaller than a preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than a preset number threshold.
In a third aspect, a storage medium is provided in an embodiment of the present application, and a computer program is stored on the storage medium, where the computer program is configured to, when executed by a processor, implement the steps of the method provided in the first aspect of the embodiment of the present application.
In a fourth aspect, an embodiment of the present application further provides an electronic device, including:
a memory having a computer program stored thereon;
a processor configured to execute the computer program in the memory to implement the steps of the method provided by the first aspect of the embodiments of the present application.
In the embodiment of the application, through a single-pass detection method and device based on voice communication, a storage medium and electronic equipment, firstly, voice code streams transmitted in a communication network are collected; then separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream; then, respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame; and finally, when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end. The single-pass can be determined by directly analyzing the voice code stream, a large amount of coding and decoding calculation and voice analysis calculation are not needed, the calculation resources are saved, the processing efficiency is high, and the method can be widely popularized in practical application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.
Fig. 1 is a schematic application environment diagram of a single-pass detection method based on voice communication according to an embodiment of the present application;
fig. 2 is a first flowchart of a single-pass detection method based on voice communication according to an embodiment of the present application;
fig. 3 is a second flowchart of a single-pass detection method based on voice communication according to an embodiment of the present application;
fig. 4 is a third flowchart illustrating a method for detecting a single-pass based on voice communication according to an embodiment of the present application;
fig. 5 is a schematic block diagram of a first module of a single-pass detection apparatus based on voice communication according to an embodiment of the present application;
fig. 6 is a schematic block diagram of a second exemplary single-pass detection apparatus based on voice communication according to an embodiment of the present disclosure;
fig. 7 is a schematic block diagram of a third module of a single-pass detection apparatus based on voice communication according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
The embodiment of the disclosure also provides a single-pass detection method based on voice communication, which is applied to the server 104. As shown in fig. 1, the server 104 is applied in a single-pass detection system based on voice communication, and the single-pass detection system based on voice communication further includes: the system comprises a calling terminal 101, a communication unit 102 and a called terminal 103, wherein the calling terminal 101 is in communication connection with the called terminal 103 through the communication unit 102, and a server 104 is in communication connection with the communication unit 102. The communication unit 102 includes, but is not limited to, a plurality of communication devices respectively located in an EPC domain, an IMS domain, and a CS domain. The communication device in EPC domain includes, but is not limited to, an evolved node b, a key control node of access network, a serving gateway and a PDN gateway, a border controller in IMS domain, a media gateway, a call session controller, an egress gateway control function, and a media gateway controller, and the CS domain includes a mobile switching center, a media gateway and a base station controller. As shown in fig. 2, the method includes:
s10: collecting voice code stream transmitted in the communication network.
The communication network may be a Voice over Long-Term Evolution (VoLTE) network. Specifically, a control instruction between the PDN gateway and the call session controller, and a voice content between the PDN gateway and the border session controller may be collected, respectively.
S12: and separating the voice code stream into a calling code stream and a called code stream based on the calling IP address or the called IP address in the voice code stream.
The voice code stream sent by the calling terminal 101 carries the calling IP address of the calling terminal 101, and the voice code stream sent by the called terminal 103 carries the called IP address of the called terminal 103. The voice code stream can be separated into a calling code stream and a called code stream by identifying the IP address carried by the voice code stream.
S14: and analyzing and processing the calling code stream and the called code stream respectively to generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame.
Obviously, under normal conditions, the data content and the frame length of the speech frames in the speech code stream vary from data frame to data frame. When the voice code stream has a single pass phenomenon (that is, the calling terminal 101 or the called terminal 103 is in a silent state), and when the voice code stream has a single pass phenomenon, the voice energy is reduced to 0, at this time, the length of the voice frame in the voice code stream and the voice content change sharply, and then the change rate also decreases sharply to a certain set threshold value and remains unchanged. Therefore, the one-pass phenomenon can be recognized by detecting the length of the voice frame, the length of the adjacent data frame in the voice code stream after the abrupt change of the voice content, and the change of the voice content.
Optionally according to an equation
Respectively analyzing and processing the calling code stream and the called code stream, wherein len (v)j) For the length of the current data frame, len (V)j-1) Is the length of the data frame preceding the current data frame, M being Vj-1And vjNumber of bytes in which the data contents of the corresponding positions are different, CjEither the first rate of change or the second rate of change.
For example, for the following contained data content sequences of adjacent data frames a1, a2, A3:
a1 is: [ F3C 99C DF C5 FE FB 012878 ],
a2 is: [ F3 DE 9C B71E 1E 497C 3F 80],
a3 is: [ F449A 26C 966B 80 ].
In a2 and a1, the data content of the corresponding position is different except that F3 and 9C are the same, and the rate of change of a2 with respect to a1 is (10-2)/10 — 80%; the length of the data frame of a2 is 10, the length of the data frame of A3 is 7, and the rate of change of A3 to a2 is 100% because the data frame lengths of a2 and A3 are not equal to each other.
S16: and judging whether the number of continuous change rates smaller than a preset first threshold in the first change rates or the second change rates is larger than a preset number threshold, and if so, executing S18.
It can be understood that when the single pass phenomenon occurs, the rate of change of the speech frame contained in the speech code stream with respect to the previous speech frame is small, and this may happen when a plurality of speech frames are continuous. Therefore, the single-pass phenomenon can be identified by detecting and judging whether the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than a preset number threshold.
S18: and determining that the calling terminal 101 or the called terminal 103 has a single-pass phenomenon.
The single-pass detection method based on voice communication provided by the embodiment of the application comprises the steps of firstly, collecting voice code streams transmitted in a communication network; then separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream; then, respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame; and finally, when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end. The single-pass can be determined by directly analyzing the voice code stream, a large amount of coding and decoding calculation and voice analysis calculation are not needed, the calculation resources are saved, the processing efficiency is high, and the method can be widely popularized in practical application.
Alternatively, a misjudgment may occur for the single-pass phenomenon determined at S18, and therefore, in order to ensure the accuracy of the determined single-pass phenomenon. As shown in fig. 3, the method further comprises:
s20: the start time, end time at which the continuous rate of change occurs is recorded.
S22: and dividing a plurality of first change rates corresponding to the calling terminal 101 or a plurality of second change rates corresponding to the called terminal 103 which are not determined to have the single-pass phenomenon into a plurality of sequence segments.
Wherein, a plurality of first change rates corresponding to the calling terminal 101 or a plurality of second change rates corresponding to the called terminal 103, which are not determined to have the single-pass phenomenon, are generated within the starting time and the ending time.
It is understood that extracting the first rate of change and the second rate of change within the start time and the end time described above is more reliable for finally determining whether the single-pass phenomenon occurs, and reduces the amount of calculation.
In the embodiment of the application, a first change rate sequence can be constructed by a plurality of first change rates, and then a plurality of sequence segments of the first change rate sequence can be constructed; and constructing a first change rate sequence by using a plurality of second change rates, and then, sequencing a plurality of sequence segments by using the second change rate sequence.
S24: a correlation coefficient is determined for each of the plurality of sequence segments with the remaining sequence segments and a sequence of correlation coefficients is generated.
For example, when the calling terminal 101 is determined to have the single-pass phenomenon, the user of the called terminal 103 usually repeatedly asks the calling terminal 101 whether to hear the voice of the party, e.g., "do you feed, feed", "hear? "," no sound "," can be heard? "and the like. Because the query voice has repeatability, the change characteristic of the voice code stream also has stronger repeatability. Thus, a correlation coefficient of each of the plurality of sequence segments with the remaining sequence segments is determined, a correlation coefficient sequence is generated, and the previously determined one-pass phenomenon is verified based on the correlation coefficient sequence. Construction of a sequence combination (P) from a plurality of sequence fragments as described above1、P2...,) for each of PiCalculating the correlation coefficient (i.e. degree of correlation) r with other sequence segments in PiObtaining the speech related sequence R ═ R1，r2...]。
For example, the method can be based on the formula
Determining a correlation coefficient of each sequence segment of the plurality of sequence segments with the rest of the sequence segments, wherein X, Y is two sequence segments of which the correlation coefficients with each other are to be determined, and r (X, Y) is the correlation coefficient. Where Var is the sample variance and cov is the covariance.
S26: and judging whether the number of correlation coefficients larger than a preset coefficient threshold value in the correlation coefficient sequence exceeds a second threshold value, and if so, executing S26.
S28: and generating a prompt for the verification success of the single-pass phenomenon.
When the number of correlation coefficients in the correlation coefficient sequence, which is greater than the preset coefficient threshold, exceeds the second threshold, based on the above, it is described that when the single pass phenomenon occurs, the user of the called terminal 103 repeatedly inquires whether the calling terminal 101 hears the voice of the party, and at this time, the actual scene where the single pass phenomenon occurs is better fitted. Therefore, a prompt is generated to indicate that the verification of the occurrence of the single-pass phenomenon is successful, and the accuracy of the determination of the occurrence of the single-pass phenomenon is ensured. The server 104 may send a prompt indicating that the verification is successful to a terminal of a network maintainer, and may notify a worker to perform maintenance and repair on communication equipment in the communication network in time.
Optionally, after S18, as shown in fig. 4, the method may further include:
s30: and acquiring a communication equipment list associated with a calling IP address and a called IP address in a calling code stream or a called code stream with a single-pass phenomenon within a preset time length.
The calling IP address and the called IP address are different, and the communication devices through which the voice code stream passes are different, and a corresponding communication device list may be queried through the specific calling IP address and the called IP address (for example, the list includes a communication device located in an EPC domain including, but not limited to, an evolved node b, a key control node of an access network, a serving gateway and a PDN gateway, a communication device located in an IMS domain boundary controller, a media gateway, a call session controller, an egress gateway control function, a media gateway controller, and a CS domain including a mobile switching center, a media gateway and a base station controller, etc.). The preset time period is 24 hours, 12 hours or 48 hours, and is not limited herein, which is determined according to the actual situation. It can be understood that a single-pass phenomenon may occur multiple times within a preset time duration, and a specific communication device may be located by detecting a concentration degree (which may be characterized by a single-pass correlation coefficient described below) of a voice code stream passing through a certain communication device when the single-pass phenomenon occurs.
S32: and determining the single-pass correlation coefficient of each communication device according to the total times of the single-pass phenomena and the times of the single-pass phenomena when each communication device in the communication device list bears the voice code stream.
For example, the communication list includes W-type network elements, each type of network element includes V communication devices, and the number of times of the single pass phenomenon when each communication device bears a voice code stream may be based on the total number of times of the single pass phenomenon, and the number of times of the single pass phenomenon when each communication device bears the voice code stream
Equation of basis
Determining a single-pass correlation coefficient for each of the communication devices, wherein Ei,jIs a one-pass correlation coefficient, Qi,jThe number of times of single pass phenomenon of the jth communication equipment in the ith type network element within the preset time length is Si,jAnd the number of times of single pass phenomenon of the ith network element in the preset time length is obtained.
S34: and sorting the single-pass correlation coefficients in a descending order, and determining the communication equipment positioned at the top N as fault equipment.
The setting of the value of N may be 1, 2, 3, etc., and may be specifically determined according to actual requirements. It will be appreciated that the more forward ranked communication devices have a higher probability of failure. After the faulty devices are determined, the identification information of each faulty device may be transmitted to a terminal of a network maintainer to prompt the network maintainer to detect the faulty devices. By means of the method, automatic detection of the fault equipment is achieved, manual testing is not needed, and a large amount of labor cost is saved.
Referring to fig. 5, the embodiment of the present application further provides a single-pass detection apparatus 500 based on voice communication, it should be noted that the basic principle and the resulting technical effect of the single-pass detection apparatus 500 based on voice communication provided by the embodiment of the present application are the same as those of the above embodiment, and for the sake of brief description, corresponding contents in the above embodiment may be referred to where this embodiment is not mentioned in part. The apparatus 500 includes an information acquisition unit 501, a code stream separation unit 502, a change rate generation unit 503, and a single-pass determination unit 504, wherein,
the information collection unit 501 is configured to collect a speech codestream transmitted in a communication network.
The code stream separation unit 502 is configured to separate the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream.
The change rate generating unit 503 is configured to analyze and process the calling code stream and the called code stream respectively to generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame respectively.
The one-way determining unit 504 is configured to determine that the one-way phenomenon occurs in the calling terminal 101 or the called terminal 103 when the number of consecutive change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than a preset number threshold.
The single-pass detection apparatus 500 based on voice communication provided in the embodiment of the present application may perform the following functions: collecting voice code stream transmitted in a communication network; separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream; respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame; when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, it is determined that the one-way phenomenon occurs at the calling terminal 101 or the called terminal 103, and the one-way phenomenon can be determined by directly analyzing the voice code stream without a large amount of coding and decoding calculation and voice analysis calculation, so that the calculation resources are saved, the processing efficiency is high, and the method can be widely popularized in practical application.
Optionally, as shown in fig. 6, the apparatus 500 further includes:
an information recording unit 601 configured to record a start time, an end time at which the continuous rate of change occurs.
A segment dividing unit 602 configured to divide a plurality of first change rates corresponding to the calling terminal 101 or a plurality of second change rates corresponding to the called terminal 103, into which the one-way phenomenon is not determined to occur, into a plurality of sequence segments.
A plurality of first change rates corresponding to the calling terminal 101 or a plurality of second change rates corresponding to the called terminal 103, which are not determined to have the single-pass phenomenon, are generated within the starting time and the ending time.
A sequence generating unit 603 configured to determine a correlation coefficient of each of the plurality of sequence segments with the remaining sequence segments, and generate a correlation coefficient sequence.
And the prompt generating unit 604 is configured to generate a prompt representing that the verification of the occurrence of the single-pass phenomenon is successful when the number of correlation coefficients in the correlation coefficient sequence, which are larger than the preset coefficient threshold value, exceeds a second threshold value.
Alternatively, the above-mentioned change rate generation unit 503 is specifically configured to calculate the rate of change according to the formula
Respectively analyzing and processing the calling code stream and the called code stream, wherein len (v)j) For the length of the current data frame, len (V)j-1) The length of the previous data frame to the current data frame,m is Vj-1And vjNumber of bytes in which the data contents of the corresponding positions are different, CjEither the first rate of change or the second rate of change.
Alternatively, the sequence generation unit 603 described above is specifically configured to be based on an equation
Determining a correlation coefficient of each sequence segment of the plurality of sequence segments with the rest of the sequence segments, wherein X, Y is two sequence segments of which the correlation coefficients with each other are to be determined, and r (X, Y) is the correlation coefficient.
In addition, as shown in fig. 7, the apparatus 500 may further include:
the list obtaining unit 701 is configured to obtain a communication device list associated with a calling IP address and a called IP address included in a calling code stream or a called code stream in which a single-pass phenomenon occurs within a preset time length.
And the association coefficient determining unit 702 is configured to determine the single-pass association coefficient of each communication device according to the total number of times of single-pass phenomena occurring and the number of times of single-pass phenomena occurring when each communication device in the communication device list bears a voice code stream.
The faulty device determination unit 703 is configured to sort the single-pass correlation coefficients in a descending order, and determine the first N communication devices as faulty devices.
Specifically, the communication list includes W types of network elements, each type of network element includes V communication devices, and the association coefficient determining unit 702 may be specifically configured to: equation of basis
Determining a single-pass correlation coefficient for each of the communication devices, wherein Ei,jIs a one-pass correlation coefficient, Qi,jThe number of times of single pass phenomenon of the jth communication equipment in the ith type network element within the preset time length is Si,jAnd the number of times of single pass phenomenon of the ith network element in the preset time length is obtained.
An embodiment of the present application further provides an electronic device, and fig. 8 is a schematic structural diagram of the electronic device provided in the embodiment of the present application. Alternatively, the electronic device may be the server in the above embodiment. As shown in fig. 8, the electronic device may have a relatively large difference due to different configurations or performances, and may include one or more processors 801 and a memory 802, where one or more stored applications or data may be stored in the memory 802. Wherein the memory 802 may be a transient storage or a persistent storage. The application program stored in memory 802 may include one or more modules (not shown), each of which may include a series of computer-executable instructions for the electronic device. Still further, the processor 801 may be configured to communicate with the memory 802 to execute a series of computer-executable instructions in the memory 802 on the electronic device. The electronic device may also include one or more power supplies 803, one or more wired or wireless network interfaces 804, one or more input-output interfaces 805, one or more keyboards 806, and the like.
In a particular embodiment, an electronic device includes a memory, a processor, and computer-executable instructions stored on the memory and executable on the processor, which when executed by the processor implement the following:
collecting voice code stream transmitted in a communication network;
separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream;
respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame;
and when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end.
When the electronic equipment executes the functions, the following beneficial effects can be achieved: the single-pass can be determined by directly analyzing the voice code stream, a large amount of coding and decoding calculation and voice analysis calculation are not needed, the calculation resources are saved, the processing efficiency is high, and the method can be widely popularized in practical application.
Further, an embodiment of the present application also provides a computer-readable storage medium for storing computer-executable instructions, which when executed by a processor implement the following process:
collecting voice code stream transmitted in a communication network;
separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream;
respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame;
and when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end.
Optionally, the computer executable instructions, when executed by the processor, may achieve the following effects:
the single-pass can be determined by directly analyzing the voice code stream, a large amount of coding and decoding calculation and voice analysis calculation are not needed, the calculation resources are saved, the processing efficiency is high, and the method can be widely popularized in practical application.
The computer-readable storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A single-pass detection method based on voice communication is characterized by comprising the following steps:
collecting voice code stream transmitted in a communication network;
separating the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream;
respectively analyzing and processing the calling code stream and the called code stream to respectively generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame;
and when the number of the continuous change rates smaller than the preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than the preset number threshold, determining that the single-pass phenomenon occurs at the calling end or the called end.
2. The method according to claim 1, wherein after determining that the calling terminal or the called terminal has the single-pass phenomenon, the method further comprises:
dividing a plurality of first change rates corresponding to a calling end or a plurality of second change rates corresponding to a called end, which are not determined to have a single-pass phenomenon, into a plurality of sequence segments;
determining a correlation coefficient of each sequence segment of the plurality of sequence segments with the rest sequence segments, and generating a correlation coefficient sequence;
and when the number of the correlation coefficients in the correlation coefficient sequence, which are larger than the preset coefficient threshold value, exceeds a second threshold value, generating a prompt for representing the successful verification of the occurrence of the single-pass phenomenon.
3. The method of claim 2, wherein after determining that the one-way phenomenon occurs at the calling terminal or the called terminal, the method further comprises:
recording the starting time and the ending time of the continuous change rate;
and a plurality of first change rates corresponding to the calling terminal or a plurality of second change rates corresponding to the called terminal, which are not determined to have the single-pass phenomenon, are generated in the starting time and the ending time.
4. The method of claim 2, wherein the analyzing the calling code stream and the called code stream respectively comprises:
equation of basis
Respectively analyzing and processing the calling code stream and the called code stream, wherein len (v)j) For the length of the current data frame, len (V)j-1) Is the length of the data frame preceding the current data frame, M being Vj-1And vjNumber of bytes in which the data contents of the corresponding positions are different, CjEither the first rate of change or the second rate of change.
5. The method of claim 2, wherein determining the correlation coefficient for each sequence segment of the plurality of sequence segments with the remaining sequence segments comprises:
equation of basis
Determining a correlation coefficient of each sequence segment of the plurality of sequence segments with the rest of the sequence segments, wherein X, Y is two sequence segments of which the correlation coefficients with each other are to be determined, and r (X, Y) is the correlation coefficient.
6. The method of claim 5, wherein after determining that the one-way phenomenon occurs at the calling terminal or the called terminal, the method further comprises:
acquiring a communication equipment list related to a calling IP address and a called IP address in a calling code stream or a called code stream with a single-pass phenomenon within a preset time length;
determining a single-pass correlation coefficient of each communication device according to the total times of the single-pass phenomena and the times of the single-pass phenomena when each communication device in the communication device list bears the voice code stream;
and sorting the single-pass correlation coefficients in a descending order, and determining the communication equipment positioned at the top N as fault equipment.
7. The method of claim 6, wherein the communication list includes W types of network elements, each type of network element includes V communication devices, and the determining the single-pass correlation coefficient of each communication device according to the total number of times of the single-pass phenomenon and the number of times of the single-pass phenomenon when each communication device bears the voice code stream includes:
equation of basis
Determining a single-pass correlation coefficient for each of the communication devices, wherein Ei,jIs a one-pass correlation coefficient, Qi,jThe number of times of single pass phenomenon of the jth communication equipment in the ith type network element within the preset time length is Si,jAnd the number of times of single pass phenomenon of the ith network element in the preset time length is obtained.
8. A single-pass detection device based on voice communication, comprising:
an information acquisition unit configured to acquire a voice code stream transmitted in a communication network;
a code stream separation unit configured to separate the voice code stream into a calling code stream and a called code stream based on a calling IP address or a called IP address in the voice code stream;
the change rate generation unit is configured to analyze and process the calling code stream and the called code stream respectively so as to generate a first change rate of each voice frame in the calling code stream relative to a previous voice frame and a second change rate of each voice frame in the called code stream relative to the previous voice frame respectively;
and the single-pass determining unit is configured to determine that a single-pass phenomenon occurs at the calling terminal or the called terminal when the number of continuous change rates smaller than a preset first threshold in the plurality of first change rates or the plurality of second change rates is larger than a preset number threshold.
9. A storage medium having stored thereon a computer program, characterized in that the program, when being executed by a processor, is adapted to carry out the steps of the method of any of claims 1-7.
10. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910673134.2A CN112291421B (en) | 2019-07-24 | 2019-07-24 | Single-pass detection method and device based on voice communication, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910673134.2A CN112291421B (en) | 2019-07-24 | 2019-07-24 | Single-pass detection method and device based on voice communication, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112291421A true CN112291421A (en) | 2021-01-29 |
| CN112291421B CN112291421B (en) | 2021-09-21 |
Family
ID=74418717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910673134.2A Active CN112291421B (en) | 2019-07-24 | 2019-07-24 | Single-pass detection method and device based on voice communication, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112291421B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113314128A (en) * | 2021-05-27 | 2021-08-27 | 哈尔滨海能达科技有限公司 | Delayed access method, device and system for voice service and related products |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100508A (en) * | 2014-05-05 | 2015-11-25 | 华为技术有限公司 | Network voice quality estimation method, device and system |
| JP2016139848A (en) * | 2015-01-26 | 2016-08-04 | 日本電信電話株式会社 | Voice quality estimation device, method and program |
| CN106791226A (en) * | 2017-01-13 | 2017-05-31 | 宇龙计算机通信科技(深圳)有限公司 | Call fault detection method and system |
| CN107846520A (en) * | 2017-10-26 | 2018-03-27 | 科大讯飞股份有限公司 | single-pass detection method and device |
| CN108074587A (en) * | 2016-11-16 | 2018-05-25 | 卢宇逍 | The interrupted method and apparatus of detection call |
| CN109561222A (en) * | 2017-09-27 | 2019-04-02 | 华为终端（东莞）有限公司 | A kind of method for detecting abnormality and device of voice data |
-
2019
- 2019-07-24 CN CN201910673134.2A patent/CN112291421B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100508A (en) * | 2014-05-05 | 2015-11-25 | 华为技术有限公司 | Network voice quality estimation method, device and system |
| JP2016139848A (en) * | 2015-01-26 | 2016-08-04 | 日本電信電話株式会社 | Voice quality estimation device, method and program |
| CN108074587A (en) * | 2016-11-16 | 2018-05-25 | 卢宇逍 | The interrupted method and apparatus of detection call |
| CN106791226A (en) * | 2017-01-13 | 2017-05-31 | 宇龙计算机通信科技(深圳)有限公司 | Call fault detection method and system |
| CN109561222A (en) * | 2017-09-27 | 2019-04-02 | 华为终端（东莞）有限公司 | A kind of method for detecting abnormality and device of voice data |
| CN107846520A (en) * | 2017-10-26 | 2018-03-27 | 科大讯飞股份有限公司 | single-pass detection method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113314128A (en) * | 2021-05-27 | 2021-08-27 | 哈尔滨海能达科技有限公司 | Delayed access method, device and system for voice service and related products |
| CN113314128B (en) * | 2021-05-27 | 2022-07-12 | 哈尔滨海能达科技有限公司 | Delayed access method, device and system for voice service and related products |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112291421B (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109005556B (en) | 4G network quality optimization method and system based on user call ticket | |
| CN108389592B (en) | Voice quality evaluation method and device | |
| JP6466334B2 (en) | Real-time traffic detection | |
| CN106998256B (en) | Communication fault positioning method and server | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN101202040A (en) | An efficient voice activity detactor to detect fixed power signals | |
| CN112738538B (en) | Live broadcasting room on-hook behavior detection method and device, electronic equipment and computer readable storage medium | |
| CN107402851B (en) | Data recovery control method and device | |
| EP3979416A1 (en) | Anomaly detection method and apparatus | |
| CN101789899A (en) | Network service quality analysis method and system | |
| JP5593944B2 (en) | Determination apparatus, determination method, and computer program | |
| CN112291421B (en) | Single-pass detection method and device based on voice communication, storage medium and electronic equipment | |
| CN104883705B (en) | A kind of the problem of data service is complained localization method and device | |
| CN106953962B (en) | A kind of call recording method and device | |
| CN114116390A (en) | Fault prediction method, device, equipment and readable storage medium | |
| CN113676926B (en) | User network sensing portrait method and device | |
| CN110535699B (en) | Infrastructure determination method and device, electronic equipment and readable storage medium | |
| CN109996254A (en) | Voice service single-pass reason localization method, device, equipment and medium | |
| CN111934800B (en) | Broadcast content monitoring method and system | |
| CN111368858B (en) | User satisfaction evaluation method and device | |
| CN108521435B (en) | Method and system for user network behavior portrayal | |
| CN116133031A (en) | Building network quality assessment method, device, electronic equipment and medium | |
| CN114121038A (en) | Sound voice testing method, device, equipment and storage medium | |
| CN113891386A (en) | Method, device and equipment for determining hidden fault of base station and readable storage medium | |
| KR101553923B1 (en) | Apparatus and method for analyzing system usage |
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 |