Call quality monitoring method and device, electronic equipment, storage medium and product
By monitoring the connectivity status of calls and using voiceprint characteristics and DTMF signals for quality evaluation, the problems of low efficiency and low accuracy of call quality monitoring in the prior art are solved, real-time and automated monitoring of call quality are realized, and user experience is improved.
Patent Information
- Application Number
- CN202510071790.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-16
- Publication Date
- 2025-05-16
AI Technical Summary
The existing call quality monitoring methods are inefficient and have low accuracy, and mainly rely on manual sampling and subjective evaluation.
By monitoring the connected state of the call, the call status of the called party is identified by the voiceprint feature of the unconnected prompt tone, and when the call is connected, the quality evaluation is performed based on the dual-tone multi-frequency DTMF signal sent by the caller.
Real-time and automated monitoring of call quality is realized, labor costs are reduced, monitoring efficiency and accuracy are improved, and the stability and reliability of the communication process are ensured.
Smart Images
Figure CN120017750A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and in particular to a call quality monitoring method, device, electronic equipment, storage medium and product. Background Art
[0002] With the continuous development of communication technology, telephone networks have covered various networks such as automatic telephone networks, satellite networks, and mobile communication networks. Although the telephone network has covered various networks such as automatic telephone networks, satellite networks, and mobile communication networks, and the overall communication quality has been significantly improved, there may still be some call quality problems that affect user perception. The existing call quality monitoring method mainly relies on manual sampling. The tester uses a call device to simulate a call at a specific time and place, and records the tester's subjective evaluation and the objective data of the simulated call. The call quality is evaluated through these data. Therefore, the existing call quality monitoring method is inefficient and inaccurate. Summary of the invention
[0003] The present invention provides a call quality monitoring method, device, electronic device, storage medium and product, which are used to solve the problem that the call quality monitoring method in the prior art is inefficient and has low accuracy.
[0004] In a first aspect, the present invention provides a call quality monitoring method, comprising: Monitor the connectivity status of calls; If it is detected that the call is not connected, the current call status of the called party is identified based on the voiceprint characteristics of the disconnection prompt tone; If it is monitored that the call is connected, a quality assessment result of the call is determined based on a dual-tone multi-frequency (DTMF) signal sent by the caller.
[0005] In one embodiment, the identifying the current call status of the called party based on the voiceprint feature of the disconnected prompt tone includes: Obtaining a disconnection prompt tone generated when the call is disconnected; Preprocessing the disconnection prompt tone to obtain a sound signal; Extracting features from the sound signal to obtain voiceprint features; Based on the voiceprint feature, the current call status of the called party is identified.
[0006] In one embodiment, the identifying the current call status of the called party based on the voiceprint feature includes: Calculating similarities between a plurality of preset voiceprint features and the voiceprint feature respectively to obtain a plurality of similarities; If the highest similarity among the multiple similarities exceeds a preset similarity threshold, the preset voiceprint feature corresponding to the highest similarity is determined as a similar voiceprint feature; The voice information associated with the similar voiceprint feature is determined as the current call status of the called party.
[0007] In one embodiment, determining the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the calling party includes: Get the DTMF signal sent by the caller; Performing frequency analysis on the DTMF signal to generate a spectrum diagram; Based on the frequency spectrum, determining a first frequency peak and a second frequency peak; the first frequency peak and the second frequency peak are the two largest frequency peaks in the frequency spectrum; a first frequency corresponding to the first frequency peak is less than a second frequency corresponding to the second frequency peak; If the first frequency peak value and the second frequency peak value do not exceed the preset peak value threshold, the DTMF signal is determined to be an abnormal signal, and a quality evaluation result of the call is determined based on the DTMF signal.
[0008] In one embodiment, determining the quality assessment result of the call based on the DTMF signal includes: Calculating a first frequency offset value of the first frequency and a second frequency offset value of the second frequency based on a position of the first frequency and a position of the second frequency; Calculating a signal-to-noise ratio of the DTMF signal based on the first frequency peak value and the second frequency peak value; Based on the first frequency offset value, the second frequency offset value and the signal-to-noise ratio, the call quality is evaluated to obtain a quality evaluation result of the call; the quality evaluation result includes at least one of signal quality information, interference information and attenuation information of the voice channel used for the call.
[0009] In one embodiment, the called party and the calling party conduct the conversation through a terminal device; the telephone network used by the called party's terminal device and the telephone network used by the calling party's terminal device are of the same type or different types.
[0010] In a second aspect, the present invention further provides a call quality monitoring device, comprising: A monitoring module, used to monitor the connectivity status of calls; A call status recognition module, for identifying the current call status of the called party based on the voiceprint features of the disconnected prompt tone if the call is detected to be disconnected; The quality assessment module is used to determine the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the caller if it is monitored that the call is connected.
[0011] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the call quality monitoring methods described above are implemented.
[0012] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the call quality monitoring methods described above are implemented.
[0013] In a fifth aspect, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by the processor, it implements the steps of any of the call quality monitoring methods described above.
[0014] The call quality monitoring method, device, electronic device, storage medium and product provided by the present invention monitor the connectivity status of the call. When it is detected that the call is not connected, the call status of the called party can be judged in real time by recognizing the voiceprint characteristics of the disconnected prompt tone, thereby providing timely feedback when the call is not established and understanding the reason why the call cannot be established; when the call is monitored to be connected, the DTMF signal is used for analysis to evaluate the quality of the connected call, which can automatically realize call quality monitoring, reduce labor costs, and improve the efficiency and accuracy of call quality monitoring, ensure the stability and reliability of the communication process, enhance the user's communication experience, and provide solid technical support for building an efficient and intelligent communication network. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1 It is a flow chart of the call quality monitoring method provided by the present invention.
[0017] Figure 2 It is a structural schematic diagram of the call quality monitoring device provided by the present invention.
[0018] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein.
[0021] Combine the following Figure 1-Figure 3 The present invention describes the call quality monitoring method, device, electronic device, storage medium and product provided by the present invention.
[0022] It should be noted that the call quality monitoring method provided by the embodiment of the present invention is implemented based on a call quality monitoring device. The call quality monitoring method provided by the present invention provides an end-to-end call quality monitoring method based on voiceprint feature recognition technology and DTMF technology, which can realize call quality monitoring of terminal devices using a variety of different networks.
[0023] Therefore, the embodiment of the present invention describes the call quality monitoring method by taking the call quality monitoring device in the call quality monitoring device as the execution subject as an example.
[0024] Combination Figure 1 , Figure 1 It is a flow chart of the call quality monitoring method provided by the present invention.
[0025] like Figure 1 As shown, the method includes the following: Step 101: monitor the connectivity status of the call; Step 102: If it is detected that the call is not connected, the current call status of the called party is identified based on the voiceprint feature of the disconnection prompt tone; Step 103: If it is detected that the call is connected, a quality assessment result of the call is determined based on a dual-tone multi-frequency (DTMF) signal sent by the caller.
[0026] Specifically, when the caller needs to communicate with the called party, the caller can use the terminal device to connect to the called party's terminal device through the telephone network. Common terminal devices include fixed-line phones, mobile phones, fax machines, WeChat phones, etc. Terminal devices are tools for users to interact directly with the network, while the telephone network provides the infrastructure and management functions of communication. Without the telephone network, terminal devices cannot connect or talk with other terminal devices.
[0027] With the continuous development of communication technology, telephone networks have covered a variety of different networks such as automatic telephone networks, satellite networks, and mobile communication networks. Among them, the automatic telephone network refers to a network that processes telephone calls through automatic switching equipment, the satellite network refers to a network that communicates through artificial satellites, and the mobile terminal refers to a device that can transmit voice and data through a mobile communication network. Different terminal devices support different communication technologies and protocols. Therefore, the telephone networks used by different terminal devices may be different, which means that the telephone network used by the terminal device of the caller and the telephone network used by the terminal device of the called party are of the same type or different types. If the telephone network used by the terminal device of the caller and the telephone network used by the terminal device of the called party are of the same type, a terminal call on the same telephone network is established between the caller and the called party; if the telephone network used by the terminal device of the caller and the telephone network used by the terminal device of the called party are of different types, a terminal call across telephone networks is established between the caller and the called party. The call quality monitoring method provided by the present invention can be compatible with the terminal call quality monitoring of the same telephone network and the terminal call quality monitoring across telephone networks at the same time, and can effectively avoid the problem of differences in call quality between different networks.
[0028] After the calling party establishes a call with the terminal device of the called party through the telephone network using the terminal device, the connectivity status of the established call, that is, the connection status of the call, is monitored.
[0029] In one case, when it is monitored that the established call is not connected, the disconnected prompt tone generated by the service provider's network system at this time is collected, such as busy tone, no answer tone, empty number prompt tone, etc., and the voiceprint features in the disconnected prompt tone are extracted. Based on the voiceprint features extracted from the disconnected prompt tone, the current call status of the called party is identified.
[0030] In another case, when it is monitored that the established call is connected, a dual-tone multi-frequency (DTMF) signal sent by the calling party to the called party is obtained, the DTMF signal is processed and analyzed, and the quality assessment of the call is implemented to obtain the quality assessment result of the call.
[0031] The call quality monitoring method provided by the present invention monitors the connectivity status of the call. When it is detected that the call is not connected, the call status of the called party can be judged in real time by using the recognition technology of the voiceprint characteristics of the disconnected prompt tone, so as to provide timely feedback when the call is not established, and understand the reason why the call cannot be established; when it is detected that the call is connected, the DTMF signal is used for analysis to evaluate the quality of the connected call, so that call quality monitoring can be automatically realized, labor costs can be reduced, and the efficiency and accuracy of call quality monitoring can be improved, so as to ensure the stability and reliability of the communication process, improve the communication experience of users, and provide solid technical support for building an efficient and intelligent communication network.
[0032] In some embodiments, based on step 102, identifying the current call status of the called party based on the voiceprint feature of the disconnected prompt tone includes: Obtaining a disconnection prompt tone generated when the call is disconnected; Preprocessing the disconnection prompt tone to obtain a sound signal; Extracting features from the sound signal to obtain voiceprint features; Based on the voiceprint feature, the current call status of the called party is identified.
[0033] Specifically, it is necessary to install sound sensors on the terminal devices of telephone networks such as automatic telephone networks, satellite networks, and mobile terminals in advance to capture call sounds in real time. When the call connection fails, the service provider's network system will generate a disconnected prompt tone. Therefore, when the system detects that the call is not connected, the generated disconnected prompt tone can be obtained.
[0034] Furthermore, the disconnected prompt tone is preprocessed, specifically including denoising, pre-emphasis and other preprocessing techniques, to finally obtain a sound signal.
[0035] Among them, denoising processing can include environmental noise recognition and suppression, application of speech enhancement technology, denoising effect evaluation and optimization, which can effectively reduce background noise and improve the clarity and intelligibility of speech signals; pre-emphasis processing can include high-frequency signal enhancement, pre-emphasis parameter adjustment and optimization, and pre-emphasis effect verification, which can enhance the high-frequency part of the speech signal, improve speech quality and improve the accuracy of subsequent processing; other pre-processing technologies can include endpoint detection and segmentation, voice activity detection, volume normalization and speech signal smoothing processing, which can further optimize signal characteristics and provide a better data basis for subsequent processing steps.
[0036] The sound signal obtained after preprocessing can be stored and managed, including but not limited to data compression and encryption, storage medium selection and optimization, data backup and recovery strategy, and storage space monitoring and expansion.
[0037] Furthermore, the time domain signal of the disconnected prompt tone is converted into a frequency domain signal through fast Fourier transform. The feature vector is calculated based on the frequency domain signal through feature extraction technology, and normalized to obtain the voiceprint feature. Feature extraction technology can use linear predictive coding (LPC), Mel frequency cepstrum coefficient (MFCC), etc. LPC is a technology used to analyze speech signals. It extracts features by predicting the current sample value based on the linear combination of past samples; MFCC is a set of features widely used in speech recognition. It simulates the human ear's perception of sound, especially in different frequency regions. The speech signal is extracted through a series of filter groups (usually Mel filter groups), and then the logarithmic energy of the filter output is calculated and discrete cosine transform is performed to obtain the cepstrum coefficients.
[0038] Furthermore, based on the voiceprint features, a match is performed in a preset voiceprint template. The preset voiceprint template is pre-set and contains multiple preset voiceprint features. Each preset voiceprint feature is associated with a voice information for identifying the caller's current call status. Therefore, when the voiceprint feature is successfully matched in the preset voiceprint template, the caller's current call status can be identified. If the voiceprint feature is not matched successfully, the voiceprint feature will be analyzed and identified to obtain the caller's current call status, and the voiceprint feature and its identified call status will be associated and added to the preset voiceprint template to provide more data sources for subsequent voiceprint feature matching.
[0039] The embodiment of the present invention realizes intelligent recognition of the current call status of the called party by accurately extracting and analyzing the voiceprint features of the disconnected prompt tone, can provide timely feedback when the call is not established, and promptly understand the reason why the call cannot be established, which helps to further improve the intelligent management level and service quality of the communication network.
[0040] According to the above content, the identifying the current call status of the called party based on the voiceprint feature includes: Calculating similarities between a plurality of preset voiceprint features and the voiceprint feature respectively to obtain a plurality of similarities; If the highest similarity among the multiple similarities exceeds a preset similarity threshold, the preset voiceprint feature corresponding to the highest similarity is determined as a similar voiceprint feature; The voice information associated with the similar voiceprint feature is determined as the current call status of the called party.
[0041] Specifically, multiple preset voiceprint features are respectively calculated with the voiceprint feature to obtain multiple similarities. The similarity calculation can sample a cosine similarity algorithm, and the cosine similarity algorithm is used to evaluate the matching degree between the real-time voiceprint feature and the preset feature template.
[0042] The calculation formula of cosine similarity is as follows: Among them, A represents the voiceprint feature, and B represents the preset voiceprint feature.
[0043] Cosine similarity can be used to compare the similarity between two voiceprint feature vectors. If the cosine similarity of two vectors is close to 1, it means that the two voiceprints are very similar; if the similarity is close to 0, it means that the voiceprints are quite different; if the similarity is negative, it means that the voiceprints are in opposite directions in the feature space.
[0044] Multiple similarity values are compared to determine the highest similarity with the largest value. If the highest similarity exceeds a preset similarity threshold, which is set according to actual conditions, the preset voiceprint feature corresponding to the highest similarity is determined as the similar voiceprint feature.
[0045] After matching similar voiceprint features, voice information associated with the similar voiceprint features is determined, and the voice information is determined as the current call status of the called party.
[0046] The embodiment of the present invention matches similar voiceprint features in a preset voiceprint template through a similarity calculation method, thereby realizing rapid and accurate identification of the call status of the called party, effectively improving the reliability of call status monitoring, and reducing the misjudgment rate.
[0047] In some embodiments, based on step 102, determining the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the calling party includes: Get the DTMF signal sent by the caller; Performing frequency analysis on the DTMF signal to generate a spectrum diagram; Based on the frequency spectrum, determining a first frequency peak and a second frequency peak; the first frequency peak and the second frequency peak are the two largest frequency peaks in the frequency spectrum; a first frequency corresponding to the first frequency peak is less than a second frequency corresponding to the second frequency peak; If the first frequency peak value and the second frequency peak value do not exceed the preset peak value threshold, the DTMF signal is determined to be an abnormal signal, and a quality evaluation result of the call is determined based on the DTMF signal.
[0048] Specifically, when the call is connected, the caller can press a number key, and the caller's terminal device will generate a corresponding DTMF signal. The DTMF signal is a dual-tone multi-frequency signal, which is composed of two audio signals of different frequencies. When the user presses a number or character key on the keyboard, each key is assigned two frequencies, one high and one low. By synthesizing the high-frequency and low-frequency signals, a corresponding DTMF signal can be generated. Therefore, when the system detects that the call is connected, it can obtain the DTMF signal sent by the caller to the called party's terminal device through the terminal device. For the obtained DTMF signal, signal preprocessing technologies such as noise suppression and signal enhancement can be adopted to preprocess the DTMF signal.
[0049] Further, Fast Fourier Transform or other signal processing techniques can be used to perform frequency analysis on the DTMF signal to generate a spectrogram, which can be used to identify the two frequency components that make up the DTMF signal. The spectrogram shows the energy distribution of the signal at different frequencies, wherein two main frequency peaks should be clearly shown, corresponding to the low-frequency and high-frequency components of the DTMF signal.
[0050] Based on the spectrum diagram, the two largest frequency peaks are identified and marked, namely the first frequency peak and the second frequency peak. The first frequency corresponding to the first frequency peak is less than the second frequency corresponding to the second frequency peak. Therefore, the first frequency peak represents the low-frequency component of the DTMF signal, and the second frequency peak represents the high-frequency component of the DTMF signal.
[0051] Generally, for a received voice signal, if it contains DTMF key signals, two very obvious frequency peaks can be seen after decoding, which means that the DTMF signal is normal. If it is difficult to see two obvious frequency peaks, there is a high probability that the DTMF signal is abnormal. Therefore, a peak threshold can be set in advance to determine whether there is an obvious frequency peak after the DTMF signal is decoded.
[0052] The first frequency peak value and the second frequency peak value are compared with the preset peak threshold value. According to the comparison result, if the first frequency peak value and the second frequency peak value both exceed the preset peak threshold value, it means that the DTMF signal is normal and the DTMF signal is strong enough. If the first frequency peak value and the second frequency peak value do not exceed the preset peak threshold value, it means that the DTMF signal is abnormal and the DTMF signal may be attenuated, interfered or otherwise affected. Further analysis and processing based on the DTMF signal is required to determine the quality assessment result of the current call.
[0053] The embodiment of the present invention effectively identifies abnormal DTMF signals by performing accurate frequency analysis and peak value detection on the DTMF signals sent by the caller, thereby achieving real-time evaluation of call quality, thereby ensuring the stability and reliability of the call.
[0054] According to the above content, the determining the quality evaluation result of the call based on the DTMF signal includes: Calculating a first frequency offset value of the first frequency and a second frequency offset value of the second frequency based on a position of the first frequency and a position of the second frequency; Calculating a signal-to-noise ratio of the DTMF signal based on the first frequency peak value and the second frequency peak value; Based on the first frequency offset value, the second frequency offset value and the signal-to-noise ratio, the call quality is evaluated to obtain a quality evaluation result of the call; the quality evaluation result includes at least one of signal quality information, interference information and attenuation information of the voice channel used for the call.
[0055] Specifically, based on the spectrum diagram, the position of the first frequency and the position of the second frequency, as well as the low-frequency position and high-frequency position of the DTMF signal standard are determined, and a difference calculation is performed based on the position of the first frequency and the standard low-frequency position to obtain a first frequency deviation value of the first frequency, and a difference calculation is performed based on the position of the second frequency and the standard high-frequency position to obtain a second frequency deviation value of the second frequency.
[0056] At the same time, based on the first frequency peak and the second frequency peak, the power value corresponding to the first frequency and the power value corresponding to the second frequency are calculated respectively, and then the two power values are summed to obtain the total signal power of the DTMF signal. In addition, the total noise power of the DTMF signal can be calculated by a spectrum analyzer.
[0057] Furthermore, based on the total signal power and total noise power of the DTMF signal, the signal-to-noise ratio of the DTMF signal is calculated, and the calculation formula is as follows: in, is the total signal power, is the total noise power.
[0058] Furthermore, based on the first frequency deviation value, the second frequency deviation value and the signal-to-noise ratio, the call quality is evaluated to obtain a call quality evaluation result. Specifically, the signal quality information of the voice channel can be evaluated by judging whether the first frequency deviation value and the second frequency deviation value are within a normal range, the interference level of the voice channel can be judged according to the size of the signal-to-noise ratio, and the attenuation degree of the voice can be judged based on the signal strength loss.
[0059] Based on the above quality assessment results, corresponding measures can be taken to improve call quality, such as adjusting the receiver's frequency response, enhancing signal processing algorithms to reduce interference, optimizing network configuration to reduce attenuation, etc. For calls with poor quality, the system can automatically issue warnings to prompt users that they may need to take action to improve the call experience. For continuous quality issues, the system can record relevant data for subsequent analysis and system optimization.
[0060] The embodiment of the present invention achieves a comprehensive evaluation of the quality of the voice channel by comprehensively calculating the first frequency deviation value, the second frequency deviation value and the signal-to-noise ratio of the DTMF signal, and can then accurately identify the signal quality, interference level and attenuation during the call, etc., thereby ensuring the accuracy and reliability of call quality monitoring, and helping to promptly improve call quality issues to ensure a good user experience during the call.
[0061] The following is a description of the call quality monitoring device provided by the present invention. The call quality monitoring device described below and the call quality monitoring method described above can be referenced to each other.
[0062] Reference Figure 2 , Figure 2 It is a structural schematic diagram of the call quality monitoring device provided by the present invention.
[0063] The call quality monitoring device comprises: The monitoring module 210 is used to monitor the connectivity status of the call.
[0064] The call status identification module 220 is used to identify the current call status of the called party based on the voiceprint feature of the disconnected prompt tone if it is detected that the call is not connected.
[0065] The quality assessment module 230 is configured to determine a quality assessment result of the call based on a dual-tone multi-frequency (DTMF) signal sent by the caller if it is detected that the call is connected.
[0066] The call quality monitoring device provided by the present invention monitors the connectivity status of the call. When it is detected that the call is not connected, the call status of the called party can be judged in real time by recognizing the voiceprint characteristics of the disconnected prompt tone, thereby providing timely feedback when the call is not established and understanding the reason why the call cannot be established; when it is detected that the call is connected, the DTMF signal is used for analysis to evaluate the quality of the connected call, which can automatically realize call quality monitoring, reduce labor costs, and improve the efficiency and accuracy of call quality monitoring, ensure the stability and reliability of the communication process, enhance the user's communication experience, and provide solid technical support for building an efficient and intelligent communication network.
[0067] Furthermore, the call status identification module 220 is also used for: Obtaining a disconnection prompt tone generated when the call is disconnected; Preprocessing the disconnection prompt tone to obtain a sound signal; Extracting features from the sound signal to obtain voiceprint features; Based on the voiceprint feature, the current call status of the called party is identified.
[0068] Furthermore, the call status identification module 220 is also used for: Calculating similarities between a plurality of preset voiceprint features and the voiceprint feature respectively to obtain a plurality of similarities; If the highest similarity among the multiple similarities exceeds a preset similarity threshold, the preset voiceprint feature corresponding to the highest similarity is determined as a similar voiceprint feature; The voice information associated with the similar voiceprint feature is determined as the current call status of the called party.
[0069] Furthermore, the quality assessment module 230 is also used for: Get the DTMF signal sent by the caller; Performing frequency analysis on the DTMF signal to generate a spectrum diagram; Based on the frequency spectrum, determining a first frequency peak and a second frequency peak; the first frequency peak and the second frequency peak are the two largest frequency peaks in the frequency spectrum; a first frequency corresponding to the first frequency peak is less than a second frequency corresponding to the second frequency peak; If the first frequency peak value and the second frequency peak value do not exceed the preset peak value threshold, the DTMF signal is determined to be an abnormal signal, and a quality evaluation result of the call is determined based on the DTMF signal.
[0070] Furthermore, the quality assessment module 230 is also used for: Calculating a first frequency offset value of the first frequency and a second frequency offset value of the second frequency based on a position of the first frequency and a position of the second frequency; Calculating a signal-to-noise ratio of the DTMF signal based on the first frequency peak value and the second frequency peak value; Based on the first frequency offset value, the second frequency offset value and the signal-to-noise ratio, the call quality is evaluated to obtain a quality evaluation result of the call; the quality evaluation result includes at least one of signal quality information, interference information and attenuation information of the voice channel used for the call.
[0071] It should be noted that the call quality monitoring device provided by the present invention can execute the call quality monitoring method described in any of the above embodiments during specific operation, which will not be described in detail in this embodiment.
[0072] Figure 3 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the call quality monitoring method, which includes: monitoring the connection status of the call; if it is detected that the call is not connected, identifying the current call status of the called party based on the voiceprint characteristics of the unconnected prompt tone; if it is detected that the call is connected, determining the quality evaluation result of the call based on the dual-tone multi-frequency DTMF signal sent by the calling party.
[0073] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0074] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the call quality monitoring method provided in the above-mentioned embodiments, the method including: monitoring the connectivity status of the call; if it is monitored that the call is not connected, identifying the current call status of the called party based on the voiceprint characteristics of the unconnected prompt tone; if it is monitored that the call is connected, determining the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the calling party.
[0075] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the call quality monitoring method provided in the above-mentioned embodiments, the method comprising: monitoring the connectivity status of the call; if it is detected that the call is not connected, identifying the current call status of the called party based on the voiceprint features of the unconnected prompt tone; if it is detected that the call is connected, determining the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the calling party.
[0076] The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. Those of ordinary skill in the art may understand and implement the present embodiment without creative effort.
[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A call quality monitoring method, characterized in that: include: Monitor the connectivity status of calls; If it is detected that the call is not connected, the current call status of the called party is identified based on the voiceprint characteristics of the disconnected prompt tone; If it is monitored that the call is connected, a quality assessment result of the call is determined based on a dual-tone multi-frequency (DTMF) signal sent by the caller.
2. The call quality monitoring method according to claim 1, characterized in that: The identifying the current call status of the called party based on the voiceprint feature of the disconnected prompt tone includes: Obtaining a disconnection prompt tone generated when the call is disconnected; Preprocessing the disconnection prompt tone to obtain a sound signal; Extracting features from the sound signal to obtain voiceprint features; Based on the voiceprint feature, the current call status of the called party is identified.
3. The call quality monitoring method according to claim 2, characterized in that: The identifying the current call status of the called party based on the voiceprint feature includes: Calculating similarities between a plurality of preset voiceprint features and the voiceprint feature respectively to obtain a plurality of similarities; If the highest similarity among the multiple similarities exceeds a preset similarity threshold, the preset voiceprint feature corresponding to the highest similarity is determined as a similar voiceprint feature; The voice information associated with the similar voiceprint feature is determined as the current call status of the called party.
4. The call quality monitoring method according to claim 1, characterized in that: Determining the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the calling party includes: Get the DTMF signal sent by the caller; Performing frequency analysis on the DTMF signal to generate a spectrum diagram; Based on the frequency spectrum, determining a first frequency peak and a second frequency peak; the first frequency peak and the second frequency peak are the two largest frequency peaks in the frequency spectrum; a first frequency corresponding to the first frequency peak is less than a second frequency corresponding to the second frequency peak; If the first frequency peak value and the second frequency peak value do not exceed the preset peak value threshold, the DTMF signal is determined to be an abnormal signal, and a quality evaluation result of the call is determined based on the DTMF signal.
5. The call quality monitoring method according to claim 4, characterized in that: The determining the quality assessment result of the call based on the DTMF signal comprises: Calculating a first frequency offset value of the first frequency and a second frequency offset value of the second frequency based on a position of the first frequency and a position of the second frequency; Calculating a signal-to-noise ratio of the DTMF signal based on the first frequency peak value and the second frequency peak value; Based on the first frequency offset value, the second frequency offset value and the signal-to-noise ratio, the call quality is evaluated to obtain a quality evaluation result of the call; the quality evaluation result includes at least one of signal quality information, interference information and attenuation information of the voice channel used for the call.
6. The call quality monitoring method according to any one of claims 1 to 5, characterized in that: The called party and the calling party conduct the conversation through a terminal device; the telephone network used by the called party's terminal device and the telephone network used by the calling party's terminal device are of the same type or different types.
7. A call quality monitoring device, characterized in that: include: A monitoring module, used to monitor the connectivity status of calls; A call status recognition module, for identifying the current call status of the called party based on the voiceprint features of the disconnected prompt tone if the call is detected to be disconnected; The quality assessment module is used to determine the quality assessment result of the call based on the dual-tone multi-frequency DTMF signal sent by the caller if it is monitored that the call is connected.
8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the call quality monitoring method according to any one of claims 1 to 6 are implemented.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the call quality monitoring method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the call quality monitoring method according to any one of claims 1 to 6 are implemented.