CN115396549A - Method for processing illegal call service device and electronic apparatus - Google Patents
Method for processing illegal call service device and electronic apparatus Download PDFInfo
- Publication number
- CN115396549A CN115396549A CN202110574454.XA CN202110574454A CN115396549A CN 115396549 A CN115396549 A CN 115396549A CN 202110574454 A CN202110574454 A CN 202110574454A CN 115396549 A CN115396549 A CN 115396549A
- Authority
- CN
- China
- Prior art keywords
- call
- format information
- illegal
- text format
- judgment result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 110
- 238000012545 processing Methods 0.000 title claims abstract description 55
- 230000008569 process Effects 0.000 claims abstract description 53
- 238000004458 analytical method Methods 0.000 claims abstract description 23
- 230000011664 signaling Effects 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 abstract description 30
- 238000012549 training Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 12
- 230000006399 behavior Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000003672 processing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013518 transcription Methods 0.000 description 2
- 230000035897 transcription Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006837 decompression Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2218—Call detail recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
- H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
- H04M3/5175—Call or contact centers supervision arrangements
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The embodiment of the invention provides a method, a device and electronic equipment for processing illegal call services, wherein the method comprises the steps of acquiring call data in a call process in real time, carrying out signaling analysis on the call data, determining calling number information and audio format information corresponding to the call data, judging whether the calling number information is consistent with a pre-stored number to be inspected to obtain a first judgment result, if the first judgment result is consistent, preprocessing the audio format information to obtain text format information corresponding to the audio format information, judging whether the call corresponding to the text format information belongs to the illegal call based on a preset illegal judgment rule to obtain a second judgment result, and processing the call corresponding to the text format information according to the second judgment result. The method and the device realize automatic processing of the illegal call service, improve the efficiency and accuracy of identifying the illegal call service, and are suitable for the real-time quality inspection scene of large-scale calls.
Description
Technical Field
The embodiment of the invention relates to the field of communication, in particular to a method and a device for processing a call violation service and electronic equipment.
Background
In recent years, along with the continuous expansion of the market scale of the voice of the government and the enterprise taking a call center and a customer service center as typical businesses, the market is developed vigorously, and meanwhile, some disordering phenomena appear in the aspect of industrial standardization. For example, some enterprises still carry out illegal red line services such as internet finance, P2P financing, credit card payment prompting, marketing fraud and the like, and operators receive a lot of complaints.
In the prior art, only a quality inspection scene facing customer service level improvement is involved, the scene aims to detect whether illegal red line service exists in the call process and whether call behaviors which do not accord with registration purposes exist in the number using process, and the call behaviors can be determined by manually acquiring offline recording and performing quality inspection analysis.
However, because the call gauge module involved in the call violation business is large, the subjectivity is strong through a manual quality inspection analysis mode, the manual workload is huge, and the efficiency and the accuracy of identifying the call violation business are reduced.
Disclosure of Invention
The embodiment of the invention provides a method and a device for processing a call violation service and electronic equipment, which are used for improving the accuracy and efficiency of identifying the call violation service.
In a first aspect, an embodiment of the present invention provides a method for processing a call violation service, including:
acquiring call data in a call process in real time;
performing signaling analysis on the call data, and determining calling number information and audio format information corresponding to the call data;
judging whether the calling number information is consistent with a pre-stored number to be tested to obtain a first judgment result;
if the first judgment result is consistent, preprocessing the audio format information to obtain text format information corresponding to the audio format information;
and judging whether the call corresponding to the text format information belongs to an illegal call or not based on a preset illegal judgment rule to obtain a second judgment result, and processing the call corresponding to the text format information according to the second judgment result.
Optionally, if the first determination result is consistent, preprocessing the audio format information to obtain text format information corresponding to the audio format information, including:
if the first judgment result is consistent, decompressing the audio format information to obtain decompressed audio format information;
and performing text conversion processing on the decompressed audio format information according to a prestored conversion rule to obtain text format information corresponding to the decompressed audio format information.
Optionally, the determining, based on the preset violation determining rule, whether the call corresponding to the text format information belongs to a violation call, to obtain a second determining result, includes:
classifying the text format information according to a preset industry and technology classifier, and determining a target industry corresponding to the text format information;
acquiring an industry keyword judgment rule corresponding to the target industry;
and judging whether the call corresponding to the text format information belongs to an illegal call according to an industry keyword judgment rule corresponding to the target industry to obtain a second judgment result.
Optionally, the processing the call corresponding to the text format information according to the second determination result includes:
if the second judgment result is that the call corresponding to the text format information belongs to an illegal call, sending a forced disconnection instruction to an agent client, wherein the forced disconnection instruction is used for indicating the agent client to disconnect the call corresponding to the text format information;
and if the second judgment result is that the call corresponding to the text format information does not belong to an illegal call, re-executing the steps of obtaining call data in the call process in real time and the later steps.
Optionally, the obtaining of call data in a call process in real time includes:
acquiring call data in a call process in real time from a mirror image port of a switch;
before the obtaining the call data in the call process in real time, the method further includes:
and configuring the number to be inspected, the network address and the port of the mirror image port of the switch, and storing configuration information.
Optionally, after the processing the call corresponding to the text format information according to the second determination result, the method further includes:
counting the illegal calling times of the calling number information every other preset time length;
and if the illegal call times of the target calling number information exceed a preset time threshold, sending the target calling number information and the illegal call times corresponding to the target calling number information to terminal equipment corresponding to maintenance personnel.
In a second aspect, an embodiment of the present invention provides a device for processing a call violation service, including:
the acquisition module is used for acquiring call data in a call process in real time;
the processing module is used for carrying out signaling analysis on the call data and determining calling number information and audio format information corresponding to the call data;
the processing module is further used for judging whether the calling number information is consistent with a pre-stored number to be inspected to obtain a first judgment result;
the processing module is further configured to, if the first determination result is consistent, pre-process the audio format information to obtain text format information corresponding to the audio format information;
the processing module is further configured to determine whether the call corresponding to the text format information belongs to an illegal call based on a preset illegal judgment rule, obtain a second judgment result, and process the call corresponding to the text format information according to the second judgment result.
In a third aspect, an embodiment of the present invention provides an electronic device, including: at least one processor and memory;
the memory stores computer execution instructions;
the at least one processor executes computer-executable instructions stored in the memory, so that the at least one processor executes the call violation traffic handling method according to any one of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer executing instruction is stored in the computer-readable storage medium, and when a processor executes the computer executing instruction, the method for processing a call violation business is implemented according to any one of the first aspect.
In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the call violation business processing method according to the first aspect and various possible designs of the first aspect is implemented.
The embodiment of the invention provides a method, a device and electronic equipment for processing illegal call services, which can acquire call data in a call process in real time after the scheme is adopted, then perform signaling analysis on the call data, determine calling number information and audio format information corresponding to the call data, judge whether the calling number information is consistent with a pre-stored number to be inspected to obtain a first judgment result, if the first judgment result is consistent, pre-process the audio format information to obtain text format information corresponding to the audio format information, judge whether the call corresponding to the text format information belongs to illegal calls based on a preset illegal judgment rule to obtain a second judgment result, further process the call corresponding to the text format information according to the second judgment result, find the call data needing quality inspection in a signaling analysis and matching mode, and automatically perform a mode of judging illegal call data needing quality inspection according to the preset judgment rule, so that the illegal call services are automatically processed, the efficiency and accuracy of call identification are improved, and the illegal calls are suitable for large-scale quality inspection scenes.
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, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic diagram of an architecture of an application system of a method for processing a call violation service according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for processing a call violation service according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a principle of a method for detecting a traffic violation in the prior art according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a method for detecting a traffic violation in the prior art according to another embodiment of the present invention;
fig. 5 is a schematic flow chart of a method for processing a call violation service according to another embodiment of the present invention;
fig. 6 is a schematic diagram of a quality inspection platform according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a call violation service processing apparatus according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
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 terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of including other sequential examples in addition to those illustrated or described. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, only a quality inspection scene facing customer service level improvement is involved, the scene aims to detect whether illegal red line service exists in the call process and whether call behaviors which do not accord with the registration purpose exist in the number use process (for example, the number is registered as customer service and the actual sales of financial products occur), and the call behaviors can be determined by manually acquiring offline sound recordings and performing quality inspection analysis. However, because the call violation business relates to a large call gauge, the subjectivity is strong through a manual quality inspection analysis mode, the manual workload is huge, and the efficiency and the accuracy of identifying the call violation business are reduced. In addition, the existing means for acquiring the sound recording is to acquire the sound recording file stored at the user side to a quality inspection platform of communication supervision in a plug-flow manner or a pull-flow manner through a file transmission protocol for quality inspection analysis, and some call centers do not have a sound recording storage function, cannot acquire offline sound recording, cannot perform illegal call detection and implementation of corresponding measures in real time (the quality inspection after the incident may be complained), and further influences the use experience of the user.
Based on the problems, the call data needing quality inspection is found through a signaling analysis and matching mode, and the call data needing quality inspection is automatically subjected to illegal call judgment through the preset illegal judgment rule, so that the automatic processing of illegal call services is realized, the technical effect of improving the efficiency and accuracy of identifying the illegal call services is achieved, and the method and the device are suitable for real-time quality inspection scenes of large-scale calls.
Fig. 1 is a schematic structural diagram of an application system of a method for processing a call violation service according to an embodiment of the present invention, and as shown in fig. 1, the application system may include a quality inspection platform 101, a call center platform 102, an agent end 103, a called end 104, and a telecommunication core network 105, where the quality inspection platform 101 is in butt joint with the call center platform 102 or various voice capability platforms, captures signaling and media transmitted by the call center platform 102 and the telecommunication core network 105 in real time, and obtains a calling source and a called source of the media by analyzing the signaling, so as to monitor a call process between the agent end and the called end, and judge whether there is a violation service in the call process.
Wherein, the quality inspection platform 101 can be deployed in a server.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a schematic flowchart of a call violation business processing method according to an embodiment of the present invention, where the method in this embodiment may be executed by a server, and specifically, may be executed by a quality inspection platform deployed in the server. As shown in fig. 2, the method of this embodiment may include:
s201: and acquiring call data in the call process in real time.
In this embodiment, in the process of a call between a user side and the user side, in order to avoid an illegal call from occurring and to avoid affecting the call experience of the user, call data in the call process can be obtained in real time in the process of a call between the user side and the user side. The call data may include calling number information, called number information, media parameter information (i.e., audio format information), and a corresponding real-time media stream number or real-time media stream identifier.
Furthermore, the call data in the call process can be acquired in real time through the protocol capturing module, and particularly, the call data in the call process can be acquired from the mirror image port of the switch in real time. Correspondingly, the protocol capture module in the quality inspection platform is connected with the switch mirror image port, the switch is connected with the call center platform, and the switch mirror image port copies signaling and media of the call center platform and telecommunication core network equipment, namely call data in the call process.
S202: and carrying out signaling analysis on the call data, and determining calling number information and audio format information corresponding to the call data.
In this embodiment, after the call data is obtained in real time, signaling analysis may be performed on a corresponding field in the call data, so as to determine calling number information and audio format information corresponding to the call data. In addition, data such as called number and real-time media stream identification corresponding to the call data can be determined.
S203: and judging whether the calling number information is consistent with a pre-stored number to be tested to obtain a first judgment result.
In this embodiment, after the calling number information is determined, the calling number information may be matched with a pre-stored number to be quality-checked, and whether the calling number information is a number to be subjected to the call violation service determination is determined.
The number to be quality-checked can be pre-stored, at least one number to be quality-checked can be pre-determined according to an actual application scene, then before call data in the call process is obtained in real time, the number to be quality-checked and a network address and a port of a mirror image port of the switch are configured, configuration information is stored, so that call data in the call process can be obtained in real time according to the configuration information in the subsequent process, calling number information in the call data is judged based on the pre-stored number to be quality-checked, and a first judgment result is obtained.
S204: and if the first judgment result is consistent, preprocessing the audio format information to obtain text format information corresponding to the audio format information.
In this embodiment, the first determination result may include two cases, where the first case is that the calling number information is consistent with the number to be quality tested, and the other case is that the calling number information is inconsistent with the number to be quality tested.
If the calling number information is consistent with the number to be quality checked, preprocessing the audio format information to obtain text format information corresponding to the audio format information, wherein the specific implementation process can include:
and if the first judgment result is consistent, decompressing the audio format information to obtain decompressed audio format information.
And performing text conversion processing on the decompressed audio format information according to a prestored conversion rule to obtain text format information corresponding to the decompressed audio format information.
Specifically, the audio format information in the real-time media stream may be first subjected to RTP protocol decapsulation and decompressed into audio format information in PCM format (pulse modulation coding). And then, voice recognition and transcription can be carried out on the audio format information in the PCM format to obtain text format information corresponding to the audio format information in the PCM format. The conversion rule may be implemented by selecting a corresponding existing method according to an actual application scenario, and is not limited in detail herein.
In addition, if the first judgment result is inconsistent, the obtained calling number information is the number which does not need to be subjected to the call violation service judgment, and the call data in other call processes can be obtained again.
S205: and judging whether the call corresponding to the text format information belongs to the illegal call based on a preset illegal judgment rule to obtain a second judgment result, and processing the call corresponding to the text format information according to the second judgment result.
In this embodiment, after the text format information is obtained, whether the call corresponding to the text format information belongs to an illegal call may be determined based on a preset illegal determination rule. Specifically, the industry to which the text format information belongs may be determined first, and then the text format information may be determined according to the keyword corresponding to the industry, so as to obtain a second determination result.
Further, the second determination result may include two cases, where the first case is that the call corresponding to the text format information belongs to an illegal call, and the other case is that the call corresponding to the text format information does not belong to an illegal call.
And if the second judgment result is that the call corresponding to the text format information belongs to an illegal call, sending a forced disconnection instruction to the seat client, wherein the forced disconnection instruction is used for indicating the seat client to disconnect the call corresponding to the text format information.
If the second judgment result is that the call corresponding to the text format information does not belong to the illegal call, the steps of obtaining the call data in the call process and the later steps are executed again, namely the call data in the newly obtained call process is continuously judged to determine whether the call process belongs to the illegal call.
By adopting the scheme, the call data in the call process can be acquired in real time, then the call data can be subjected to signaling analysis, the calling number information and the audio format information corresponding to the call data are determined, whether the calling number information is consistent with the pre-stored number to be quality checked or not is judged, a first judgment result is obtained, if the first judgment result is consistent, the audio format information is preprocessed, the text format information corresponding to the audio format information is obtained, whether the call corresponding to the text format information belongs to illegal call or not is judged based on the preset illegal judgment rule, a second judgment result is obtained, the call corresponding to the text format information is further processed according to the second judgment result, the call data needing quality check is found in a signaling analysis and matching mode, and the call data needing quality check is automatically subjected to a call violation judgment mode through the preset illegal judgment rule, so that the automatic processing of the call service is realized, the efficiency and the accuracy of call service identification are improved, and the call data are suitable for large-scale real-time quality check scenes.
Based on the method of fig. 2, the present specification also provides some specific embodiments of the method, which are described below.
In addition, in another embodiment, the determining, based on a preset violation determination rule, whether a call corresponding to the text format information belongs to a violation call to obtain a second determination result may specifically include:
classifying the text format information according to a preset industry and technology classifier, and determining a target industry corresponding to the text format information. And acquiring an industry keyword judgment rule corresponding to the target industry. And judging whether the call corresponding to the text format information belongs to the illegal call according to an industry keyword judgment rule corresponding to the target industry to obtain a second judgment result.
In this embodiment, fig. 3 is a schematic diagram of a principle of a method for detecting a call violation service in the prior art according to an embodiment of the present invention, as shown in fig. 3, in this embodiment, call content including a violation call is used as a training sample, training is performed in a machine learning manner, a violation call recognition model is constructed, a call audio between a customer service and a customer is called from a call record library, and a series of preprocessing processes such as framing, phoneme information extraction, word association matching and the like are performed, and then, pattern matching is performed on the violation call recognition model, so as to finally determine whether a violation call exists. Fig. 4 is a schematic diagram illustrating a principle of a method for detecting a call violation business in the prior art according to another embodiment of the present invention, as shown in fig. 4, in this embodiment, pre-labeled keyword data may be used as a training sample, a machine learning manner is used for training, a keyword acoustic recognition model is constructed by extracting filter bank features, perceptual linear prediction coefficient features, sound frequency features, and the like, and a keyword of the to-be-detected speech data is recognized, and if a violation keyword (e.g., marketing, fraud) is labeled in the training sample, whether a violation call exists may be determined by this method. However, in the two methods, the existing recording acquisition means acquires the recording file stored on the user side to a quality inspection platform of a communication supervision in a push-streaming or pull-streaming manner through a file transfer protocol for quality inspection analysis, and illegal call detection and implementation of corresponding measures (such as forcible release) cannot be performed in real time. Although some user call center systems have the function of real-time quality inspection, all the systems are enterprise self-service scenes oriented to customer service level improvement, namely, whether the speech skills of customer service personnel of manual agents meet service specifications or not is checked, the emotional willingness of interlocutors is judged, whether forbidden words exist or not is judged, and the goal difference from a communication supervision quality inspection scene is large.
The embodiment of the invention can receive the imported industry recording, train the industry speech classifier, receive the imported keyword library text, train the keyword judger, classify the text format information by industry after the training is finished, judge the illegal words corresponding to a certain industry, and check whether the illegal words are used according to the registered use of the report, such as logistics industry, express delivery and O2O, and no marketing words exist. On one hand, whether a business prohibited to be developed exists is checked, for example, the financial loan should not have words for urging to pay, P2P words and the like.
In another embodiment, after processing the call corresponding to the text format information according to the second determination result, the method may further include:
and counting the illegal call times of the calling number information every other preset time length.
And if the illegal call times of the target calling number information exceed a preset time threshold, sending the target calling number information and the illegal call times corresponding to the target calling number information to terminal equipment corresponding to maintenance personnel.
In this embodiment, if the number of illegal calls of a target calling number information within a preset duration exceeds a preset number threshold, the target calling number information and the number of illegal calls corresponding to the target calling number information may be sent to a terminal device corresponding to a maintenance worker, so that the maintenance worker further processes the target calling number information, and exemplarily, a number sealing process may be performed.
The preset duration can be set according to the actual application scene in a user-defined manner, and is not discussed in detail here.
Fig. 5 is a schematic flow chart of a method for processing a call violation service according to another embodiment of the present invention, as shown in fig. 5, in this embodiment, the method may include:
And 2, analyzing the signaling, and extracting calling number information and audio format information.
And 3, matching the extracted calling number information with the number to be tested to obtain a first judgment result, if the first judgment result is yes, entering the step 4, and if the first judgment result is not, returning to the step 3.
Step 4, extracting the audio format information (namely the media stream) corresponding to the matching number;
and 5, carrying out audio decoding on the extracted media stream, and decoding the compressed media stream into an uncompressed audio stream.
And 6, carrying out voice recognition and transcription on the audio stream to generate a context dialog of the text.
And 7, classifying the transcribed contextual dialog by the trade speech technology.
And 8, carrying out keyword judgment on the context dialog classified according to the industry.
And 9, judging whether the call is an illegal call or not to obtain a second judgment result, if so, entering the step 10, and if not, returning to the step 3.
And step 10, performing intervention operation on the illegal number, such as feeding back to a call center seat client to inform to forcibly tear down the call.
And step 11, counting the illegal call frequency of the number on the day or the week.
And 12, outputting the statistical result of a certain time unit, so as to be convenient for archiving or presentation.
Fig. 6 is a schematic diagram of an architecture of a quality inspection platform according to an embodiment of the present invention, as shown in fig. 6, in this embodiment, the architecture may include: the device comprises a protocol and analysis grabbing unit, a judgment output module, a voice processing unit, a natural language understanding unit and a training unit. The speech processing unit can comprise an audio decoding module and a speech recognition module, the natural language understanding unit can comprise an industry speech technology classifier and a keyword decision device, and the training unit can comprise an industry speech technology feature classification training module and a keyword feature classification training module.
One end of the quality inspection platform is connected with a switch mirror image port, the switch is connected with the call center platform, the mirror image port duplicates signaling and media of the call center platform and telecommunication core network equipment, and the quality inspection platform is provided with a recording import interface and a text import interface.
Furthermore, the functional roles of each unit of the quality inspection platform can be as follows:
protocol capture and analysis unit: the method is used for capturing signaling and media at the mirror image port of the switch, and extracting corresponding calling number information, called number information, audio format information and corresponding real-time media stream numbers through analysis of corresponding fields in the signaling.
A decision output module: and the comprehensive judgment module is used for comprehensively judging the sound recording analysis result, the number corresponding to the sound recording and the service corresponding to the number to obtain a conclusion whether the violation is suspected.
A voice processing unit: comprising an audio decoding module and a speech recognition module for converting a real-time media stream into text.
An audio decoding module: for RTP protocol decapsulation and decompression into PCM format (pulse modulation coding) of the audio stream in the real-time media stream.
A voice recognition module: for speech recognition of the decompressed audio stream to text.
Natural language understanding unit: the system comprises an industry speech classifier and an industry keyword decider, which are used for understanding the conversation of the transcribed text in the previous and later periods, analyzing and classifying the conversation into a certain industry and judging according to the industry keywords.
An industry speech technology classifier: and the method is used for classifying the transcribed text conversations into industries.
An industry keyword decider: the method is used for judging illegal words corresponding to a certain industry, and on one hand, whether calling number information is used according to the registered use of the report is checked, and marketing words should not exist in logistics industry, express delivery and O2O. On one hand, whether a business prohibited to be developed exists is checked, for example, the financial loan should not have words for urging to pay, P2P words and the like.
A training unit: the system comprises an industry dialect feature classification training module and a keyword feature classification training module, and is used for training a natural language understanding unit.
An industry dialect feature classification training module: and the system is used for receiving the imported industry voice record and training the industry speech classifier.
A keyword feature classification training module: and the system is used for receiving the imported keyword library text and training the keyword judger.
Based on the same idea, an embodiment of the present specification further provides a device corresponding to the method, and fig. 7 is a schematic structural diagram of a device for processing a call violation service according to an embodiment of the present invention, and as shown in fig. 7, the device may include:
the obtaining module 701 is configured to obtain call data in a call process in real time.
In this embodiment, the obtaining module 701 is further configured to:
and acquiring the call data in the call process in real time from the image port of the switch.
And configuring the number to be inspected, the network address and the port of the mirror image port of the switch, and storing configuration information.
A processing module 702, configured to perform signaling analysis on the call data, and determine calling number information and audio format information corresponding to the call data.
The processing module 702 is further configured to determine whether the calling number information is consistent with a pre-stored number to be quality checked, so as to obtain a first determination result.
The processing module 702 is further configured to, if the first determination result is consistent, perform preprocessing on the audio format information to obtain text format information corresponding to the audio format information.
In this embodiment, the processing module 702 is further configured to:
and if the first judgment result is consistent, decompressing the audio format information to obtain decompressed audio format information.
And performing text conversion processing on the decompressed audio format information according to a pre-stored conversion rule to obtain text format information corresponding to the decompressed audio format information.
The processing module 702 is further configured to determine whether the call corresponding to the text format information belongs to an illegal call based on a preset illegal determination rule, obtain a second determination result, and process the call corresponding to the text format information according to the second determination result.
In this embodiment, the processing module 702 is further configured to:
and if the second judgment result is that the call corresponding to the text format information belongs to an illegal call, sending a forced disconnection instruction to an agent client, wherein the forced disconnection instruction is used for indicating the agent client to disconnect the call corresponding to the text format information.
And if the second judgment result is that the call corresponding to the text format information does not belong to an illegal call, re-executing the steps of obtaining call data in the call process and the following steps.
In another embodiment, the processing module 702 is further configured to:
classifying the text format information according to a preset industry and technology classifier, and determining a target industry corresponding to the text format information.
And acquiring an industry keyword judgment rule corresponding to the target industry.
And judging whether the call corresponding to the text format information belongs to an illegal call according to an industry keyword judgment rule corresponding to the target industry to obtain a second judgment result.
In another embodiment, the processing module 702 is further configured to:
and counting the illegal call times of the calling number information every other preset time length.
And if the illegal call times of the target calling number information exceed a preset time threshold, sending the target calling number information and the illegal call times corresponding to the target calling number information to terminal equipment corresponding to maintenance personnel.
The apparatus provided in the embodiment of the present invention may implement the method in the embodiment shown in fig. 2, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 8 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention, and as shown in fig. 8, a device 800 according to this embodiment includes: at least one processor 801 and a memory 802. The processor 801 and the memory 802 are connected by a bus 803.
In a specific implementation, at least one processor 801 executes computer-executable instructions stored by the memory 802, so that at least one processor 801 executes the method in the above-described method embodiments.
For a specific implementation process of the processor 801, reference may be made to the above method embodiments, which have similar implementation principles and technical effects, and details of this embodiment are not described herein again.
In the embodiment shown in fig. 8, it should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose processors, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor.
The memory may comprise high speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present application are not limited to only one bus or one type of bus.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer execution instruction is stored in the computer-readable storage medium, and when a processor executes the computer execution instruction, the call violation service processing method of the embodiment of the method is realized.
An embodiment of the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the method for processing a call violation service is implemented.
The computer-readable storage medium may be any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk. A readable storage medium may be any available medium that can be accessed by a general purpose or special purpose computer.
An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium may also be an integral part of the processor. The processor and the readable storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the readable storage medium may also reside as discrete components in the apparatus.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for processing a call violation service is characterized by comprising the following steps:
acquiring call data in a call process in real time;
performing signaling analysis on the call data, and determining calling number information and audio format information corresponding to the call data;
judging whether the calling number information is consistent with a pre-stored number to be tested to obtain a first judgment result;
if the first judgment result is consistent, preprocessing the audio format information to obtain text format information corresponding to the audio format information;
and judging whether the call corresponding to the text format information belongs to an illegal call or not based on a preset illegal judgment rule to obtain a second judgment result, and processing the call corresponding to the text format information according to the second judgment result.
2. The method according to claim 1, wherein if the first determination result is that the audio format information is consistent, preprocessing the audio format information to obtain text format information corresponding to the audio format information includes:
if the first judgment result is consistent, decompressing the audio format information to obtain decompressed audio format information;
and performing text conversion processing on the decompressed audio format information according to a prestored conversion rule to obtain text format information corresponding to the decompressed audio format information.
3. The method according to claim 1, wherein the determining whether the call corresponding to the text format information belongs to an illegal call based on a preset illegal determination rule to obtain a second determination result includes:
classifying the text format information according to a preset industry and technology classifier, and determining a target industry corresponding to the text format information;
acquiring an industry keyword judgment rule corresponding to the target industry;
and judging whether the call corresponding to the text format information belongs to an illegal call according to an industry keyword judgment rule corresponding to the target industry to obtain a second judgment result.
4. The method according to claim 1, wherein the processing the call corresponding to the text format information according to the second determination result includes:
if the second judgment result is that the call corresponding to the text format information belongs to an illegal call, sending a forced disconnection instruction to an agent client, wherein the forced disconnection instruction is used for indicating the agent client to disconnect the call corresponding to the text format information;
and if the second judgment result is that the call corresponding to the text format information does not belong to an illegal call, re-executing the steps of obtaining call data in the call process in real time and the later steps.
5. The method according to any one of claims 1 to 4, wherein the obtaining the call data in the call process in real time comprises:
acquiring call data in a call process in real time from a mirror image port of a switch;
before the obtaining the call data in the call process in real time, the method further includes:
and configuring the number to be inspected, the network address and the port of the mirror image port of the switch, and storing configuration information.
6. The method according to any one of claims 1 to 4, wherein after the processing the call corresponding to the text format information according to the second determination result, the method further includes:
counting the illegal calling times of the calling number information every other preset time length;
and if the illegal call times of the target calling number information exceed a preset time threshold, sending the target calling number information and the illegal call times corresponding to the target calling number information to terminal equipment corresponding to maintenance personnel.
7. A conversation violation service processing device is characterized by comprising:
the acquisition module is used for acquiring call data in a call process in real time;
the processing module is used for carrying out signaling analysis on the call data and determining calling number information and audio format information corresponding to the call data;
the processing module is further used for judging whether the calling number information is consistent with a pre-stored number to be tested to obtain a first judgment result;
the processing module is further configured to, if the first determination result is consistent, pre-process the audio format information to obtain text format information corresponding to the audio format information;
the processing module is further configured to determine whether the call corresponding to the text format information belongs to an illegal call based on a preset illegal judgment rule, obtain a second judgment result, and process the call corresponding to the text format information according to the second judgment result.
8. An electronic device, comprising: at least one processor and memory;
the memory stores computer-executable instructions;
the at least one processor executing the computer-executable instructions stored by the memory causes the at least one processor to perform the call violation traffic handling method of any of claims 1-6.
9. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when executed by a processor, the computer-executable instructions implement the call violation traffic handling method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements a call violation traffic handling method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110574454.XA CN115396549A (en) | 2021-05-25 | 2021-05-25 | Method for processing illegal call service device and electronic apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110574454.XA CN115396549A (en) | 2021-05-25 | 2021-05-25 | Method for processing illegal call service device and electronic apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115396549A true CN115396549A (en) | 2022-11-25 |
Family
ID=84113955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110574454.XA Pending CN115396549A (en) | 2021-05-25 | 2021-05-25 | Method for processing illegal call service device and electronic apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115396549A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956897A (en) * | 2023-09-20 | 2023-10-27 | 湖南财信数字科技有限公司 | Method, device, computer equipment and storage medium for processing hidden advertisement |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7711104B1 (en) * | 2004-03-31 | 2010-05-04 | Avaya Inc. | Multi-tasking tracking agent |
| CN107734128A (en) * | 2017-09-28 | 2018-02-23 | 努比亚技术有限公司 | One kind swindle number identification method and equipment |
| CN108763499A (en) * | 2018-05-30 | 2018-11-06 | 平安科技（深圳）有限公司 | Calling quality detecting method, device, equipment and storage medium based on intelligent sound |
| CN109429230A (en) * | 2017-08-28 | 2019-03-05 | 中国移动通信集团浙江有限公司 | A kind of communication swindle recognition methods and system |
| CN109902937A (en) * | 2019-01-31 | 2019-06-18 | 平安科技（深圳）有限公司 | Quality detecting method, device, computer equipment and the storage medium of task data |
| CN110310663A (en) * | 2019-05-16 | 2019-10-08 | 平安科技（深圳）有限公司 | Words art detection method, device, equipment and computer readable storage medium in violation of rules and regulations |
| WO2019210557A1 (en) * | 2018-05-03 | 2019-11-07 | 平安科技（深圳）有限公司 | Voice quality inspection method and device, computer device and storage medium |
| CN111641757A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Real-time quality inspection and auxiliary speech pushing method for seat call |
| CN111698374A (en) * | 2020-06-28 | 2020-09-22 | 中国银行股份有限公司 | Customer service voice processing method and device |
| CN112804400A (en) * | 2020-12-31 | 2021-05-14 | 中国工商银行股份有限公司 | Customer service call voice quality inspection method and device, electronic equipment and storage medium |
-
2021
- 2021-05-25 CN CN202110574454.XA patent/CN115396549A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7711104B1 (en) * | 2004-03-31 | 2010-05-04 | Avaya Inc. | Multi-tasking tracking agent |
| CN109429230A (en) * | 2017-08-28 | 2019-03-05 | 中国移动通信集团浙江有限公司 | A kind of communication swindle recognition methods and system |
| CN107734128A (en) * | 2017-09-28 | 2018-02-23 | 努比亚技术有限公司 | One kind swindle number identification method and equipment |
| WO2019210557A1 (en) * | 2018-05-03 | 2019-11-07 | 平安科技（深圳）有限公司 | Voice quality inspection method and device, computer device and storage medium |
| CN108763499A (en) * | 2018-05-30 | 2018-11-06 | 平安科技（深圳）有限公司 | Calling quality detecting method, device, equipment and storage medium based on intelligent sound |
| CN109902937A (en) * | 2019-01-31 | 2019-06-18 | 平安科技（深圳）有限公司 | Quality detecting method, device, computer equipment and the storage medium of task data |
| CN110310663A (en) * | 2019-05-16 | 2019-10-08 | 平安科技（深圳）有限公司 | Words art detection method, device, equipment and computer readable storage medium in violation of rules and regulations |
| CN111641757A (en) * | 2020-05-15 | 2020-09-08 | 北京青牛技术股份有限公司 | Real-time quality inspection and auxiliary speech pushing method for seat call |
| CN111698374A (en) * | 2020-06-28 | 2020-09-22 | 中国银行股份有限公司 | Customer service voice processing method and device |
| CN112804400A (en) * | 2020-12-31 | 2021-05-14 | 中国工商银行股份有限公司 | Customer service call voice quality inspection method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王大伟;: "基于语音分析技术的电力客户服务质量检测与分析探究", 电子测试, no. 05, 25 March 2014 (2014-03-25), pages 100 - 101 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116956897A (en) * | 2023-09-20 | 2023-10-27 | 湖南财信数字科技有限公司 | Method, device, computer equipment and storage medium for processing hidden advertisement |
| CN116956897B (en) * | 2023-09-20 | 2023-12-15 | 湖南财信数字科技有限公司 | Method, device, computer equipment and storage medium for processing hidden advertisement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112804400B (en) | Customer service call voice quality inspection method and device, electronic equipment and storage medium | |
| CN110910901B (en) | Emotion recognition method and device, electronic equipment and readable storage medium | |
| US9171547B2 (en) | Multi-pass speech analytics | |
| US10049661B2 (en) | System and method for analyzing and classifying calls without transcription via keyword spotting | |
| US9015046B2 (en) | Methods and apparatus for real-time interaction analysis in call centers | |
| US8412530B2 (en) | Method and apparatus for detection of sentiment in automated transcriptions | |
| US8145562B2 (en) | Apparatus and method for fraud prevention | |
| US8798255B2 (en) | Methods and apparatus for deep interaction analysis | |
| US8326643B1 (en) | Systems and methods for automated phone conversation analysis | |
| US8311824B2 (en) | Methods and apparatus for language identification | |
| CA2564760C (en) | Speech analysis using statistical learning | |
| US20090043573A1 (en) | Method and apparatus for recognizing a speaker in lawful interception systems | |
| US9947320B2 (en) | Script compliance in spoken documents based on number of words between key terms | |
| CN111597818B (en) | Call quality inspection method, device, computer equipment and computer readable storage medium | |
| CN110598008B (en) | Method and device for detecting quality of recorded data and storage medium | |
| CN111522947A (en) | Method and system for processing complaint work order | |
| CN111147669A (en) | Full real-time automatic service quality inspection system and method | |
| CN111831875A (en) | Data processing method, device, equipment and storage medium | |
| CN112509561A (en) | Emotion recognition method, device, equipment and computer readable storage medium | |
| CN115396549A (en) | Method for processing illegal call service device and electronic apparatus | |
| CN111126071A (en) | Method and device for determining questioning text data and data processing method of customer service group | |
| CN112333709B (en) | Cross-network fraud association analysis method and system and computer storage medium | |
| JP2016143909A (en) | Telephone conversation content analysis display device, telephone conversation content analysis display method, and program | |
| CN110728145A (en) | Method for establishing natural language understanding model based on recording conversation | |
| CN111881272A (en) | Real-time early warning system and method for telephone service |
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 |