Methods, devices, electronic equipment and storage media for testing audio and video call quality

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for audio and video call quality detection, relating to the field of call technology. The method includes: before a call, detecting multiple first indicators of a terminal to obtain a first risk score; collecting call data during the call; during the call, detecting the terminal and the call data based on the first risk score to obtain a second risk score; after the call ends, determining a quality inspection intensity score based on the first risk score and the second risk score; and performing quality inspection on the call data based on the quality inspection intensity score to obtain a quality inspection result.

Description

Technical Field

[0001] This disclosure relates to the field of call technology, and in particular to a method, apparatus, electronic device and storage medium for detecting audio and video call quality. Background Technology

[0002] Current audio and video call quality inspection solutions mostly focus on only one stage—either pre-call inspection, in-call monitoring, or post-call analysis. The data from each stage is fragmented, and troubleshooting requires manually searching through multiple logs, which is very inefficient.

[0003] Some solutions also cover multiple stages, but the data between stages is not shared. For example, if a problem is detected before a call, the monitoring during the call will not be adjusted, and there is no linkage between the two stages. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for detecting audio and video call quality, in order to at least solve the above-mentioned technical problems existing in the prior art.

[0005] According to a first aspect of this disclosure, a method for detecting audio and video call quality is provided, the method comprising: Before the call, several primary indicators of the terminal are tested to obtain a primary risk score; Collect call data during the call process; During the call, based on the first risk score, the terminal and the call data are detected to obtain a second risk score; After the call ends, a quality inspection intensity score is determined based on the first risk score and the second risk score. The call data is inspected based on the quality inspection intensity score to obtain the quality inspection result.

[0006] In one possible implementation, the step of detecting multiple first indicators of the terminal before the call to obtain a first risk score includes: Before the call, identify any abnormal scores for each primary metric; Based on the abnormal scores of each primary indicator and the corresponding weight of each primary indicator, the risk score of each primary indicator is determined. The first risk score is determined by summing the risk scores of all first indicators.

[0007] In one possible implementation, during the call, the step of detecting the terminal and the call data based on the first risk score to obtain a second risk score includes: If the first risk score is greater than the first preset threshold, then the first indicator whose abnormal score is greater than the second preset threshold is determined as the target first indicator. During the call, a second target indicator corresponding to the first target indicator is determined in the terminal and the call data; The sampling period of the second indicator in the terminal and the call data is adjusted, as are the abnormal preset threshold and abnormal level corresponding to the target second indicator; Based on the adjusted data, all second indicators in the terminal and the call data are detected to obtain a second risk score.

[0008] In one possible implementation, determining the quality inspection intensity score based on the first risk score and the second risk score after the call ends includes: Determine the linkage penalty factor and its corresponding weight; Determine the weights corresponding to the first risk score and the second risk score, respectively; The quality inspection intensity score is determined by summing the products of the first risk score, the second risk score, and the linkage penalty factor with their respective weights.

[0009] In one embodiment, the quality inspection intensity score is divided into a first interval, a second interval, and a third interval in ascending order, with each interval corresponding to a different intensity of quality inspection. The higher the quality inspection intensity score, the greater the corresponding quality inspection intensity. The step of performing quality inspection on the call data based on the quality inspection intensity score to obtain the quality inspection result includes: In response to the quality inspection intensity score being in the first range, the call data is subjected to a quality inspection of the first intensity. In response to the quality inspection intensity score being in the second range, the call data is subjected to a second intensity of quality inspection; In response to the quality inspection intensity score being in the third interval, the call data is subjected to a third-intensity quality inspection; Based on the quality inspection of the first intensity, the second intensity, or the third intensity, anomalies in the call data are determined.

[0010] In one possible implementation, after determining the anomaly present in the call data, the method further includes: For each abnormal issue in the call data, at least one root cause score is calculated according to the root cause scoring formula; The root cause corresponding to the highest root cause score is identified as the primary root cause of the abnormal problem.

[0011] In one possible implementation, for each anomalous issue in the call data, at least one root cause score is calculated according to a root cause scoring formula, including: The root cause scoring formula is as follows:

[0012] in, Root cause scoring, To determine the relevance of this anomaly before and during the call, To determine the relevance of this anomaly during and after the call, To determine the severity of this anomaly, , , They are respectively , and The weight.

[0013] According to a second aspect of this disclosure, an audio / video call quality detection device is provided, the device comprising: The first quality inspection unit is used to test multiple primary indicators of the terminal before a call to obtain a primary risk score. The data acquisition unit is used to collect call data during the call process; The second quality inspection unit is used to inspect the terminal and the call data during the call based on the first risk score to obtain a second risk score. The third quality inspection unit is used to determine the quality inspection intensity score based on the first risk score and the second risk score after the call ends. The fourth quality inspection unit is used to perform quality inspection on the call data based on the quality inspection intensity score, and obtain the quality inspection result.

[0014] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and a memory communicatively connected to said at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described in this disclosure.

[0015] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the methods described in this disclosure.

[0016] The audio and video call quality detection method, apparatus, electronic device, and storage medium disclosed herein can achieve quality detection of audio and video calls throughout their entire lifecycle by detecting terminal indicators before the call, conducting real-time monitoring based on the results of the previous detection during the call, and determining the quality inspection intensity score and performing corresponding quality inspections after the call by combining the detection results of the first two stages. This effectively solves the problem of independent quality inspection stages and fragmented data in existing technologies. The detection results of each stage are interconnected and work synergistically, which can significantly improve the accuracy and comprehensiveness of anomaly detection and reduce the probability of missed detections and false detections.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0018] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which: In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts.

[0019] Figure 1 A flowchart of the audio / video call quality detection method provided in the embodiments of this disclosure; Figure 2 This is a schematic diagram of the structure of the audio / video call quality detection device provided in the embodiments of this disclosure; Figure 3 A schematic diagram of the composition structure of an electronic device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0020] To make the objectives, features, and advantages of this disclosure more apparent and understandable, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0021] This disclosure provides a method for detecting audio and video call quality. This method can be implemented by an audio and video call quality detection system, which includes a unified access layer, a pre-test unit, a mid-test unit, a post-test unit, a linkage control unit, and a data aggregation and tracing unit.

[0022] The unified access layer is responsible for receiving audio and video call requests from mobile devices, H5 terminals, or other terminals, and identifying the terminal type, service type, and session context information. The pre-call self-check unit performs an environmental self-check on the access terminal before the call is established. The in-call monitoring unit collects and analyzes multi-dimensional monitoring data in real time during the call. The post-call quality inspection unit performs corresponding quality inspection tasks on the recorded files based on the current risk level after the call ends. The linkage control unit is responsible for executing cross-stage linkage algorithms, generating protocol messages, and issuing control commands to each stage. The data merging and tracing unit is responsible for merging structured event data from different stages, constructing causal chains, and outputting tracing results.

[0023] The unified access layer also assigns a unique identifier, call_id, to each audio and video call. All subsequent events, policies, reports, and tasks are bound to this call_id, ensuring that data is traceable throughout the call's lifecycle.

[0024] The linkage control unit maintains a unified event model, which includes the following fields: call_id represents a complete audio / video call; event_id represents the current event and is a unique identifier for that event; `trace_parent_id` represents the upstream event associated with the current event, used to mark which earlier event caused the event, providing a basis for constructing the causal chain; The term "stage" indicates the phase of an event, which includes three phases: before the call, during the call, and after the call. event_type indicates the event type, which describes what problem or action the event describes, such as permission exceptions, network problems, etc. terminal_type indicates the terminal type, such as mobile terminal, H5 terminal, etc. metric_key and metric_value represent specific monitoring metrics and their values, such as CPU utilization of 80% and write latency of 2 seconds; risk_level indicates the risk level of the event, which can usually be divided into low risk, medium risk and high risk; action_code indicates the type of action triggered by this event, specifying the exact means to be used to resolve the problem after it is discovered; The timestamp indicates the time when the event was generated.

[0025] This unified event model allows heterogeneous data generated before, during, and after a call to be expressed using the same field structure, avoiding the problem of broken data mapping between different stages. The data format is unified, and data from different stages can be linked together, eliminating the need to search for corresponding relationships when troubleshooting.

[0026] Figure 1 A flowchart of the audio / video call quality detection method provided in the embodiments of this disclosure is shown below. Figure 1 As shown, the method includes: Step 101: Before the call, multiple primary indicators of the terminal are detected to obtain a primary risk score.

[0027] The phrase "before the call" here can refer to the time before a user receives an incoming call or makes a call.

[0028] The terminal can be a mobile device, such as a mobile phone or tablet, or an H5 terminal. For mobile devices, the first indicator includes several items from CPU status, memory status, camera permissions, microphone permissions, audio capture status, video capture status, and service connectivity status. For H5 terminals, the first indicator includes several items from browser type, WebRTC (Web Real-Time Communications) support status, speaker status, permission status, and service connectivity status.

[0029] For mobile and H5 platforms, the system configures different terminal capability description fields and detection rules. Mobile platforms focus on detecting local hardware permissions, resource status, and data collection capabilities; H5 platforms focus on detecting the browser environment, WebRTC support status, and page permission status.

[0030] Although the primary indicators differ across terminals, they all ultimately output structured data to the linkage control unit using a unified event model and a unified interaction protocol. This allows for differentiated detection and unified control of different terminals without altering the overall linkage logic.

[0031] In one embodiment, prior to the call, several first indicators of the terminal are detected to obtain a first risk score, including: Before the call, identify any abnormal scores for each primary metric; Based on the abnormal scores of each primary indicator and the corresponding weight of each primary indicator, the risk score of each primary indicator is determined. The first risk score is determined by summing the risk scores of all first indicators.

[0032] Specifically, the linkage control unit can calculate a first risk score based on the detection results of the terminal before the call, using the following formula:

[0033] in, As the first risk score, This represents the weight of the i-th first indicator. This represents the abnormal score of the i-th primary indicator.

[0034] In one specific embodiment, microphone permissions are important, and therefore have a higher weight.

[0035] Anomaly scores can be assigned discrete values, such as 0 for normal, 0.3 for minor anomaly, 0.6 for obvious anomaly, and 1.0 for severe anomaly.

[0036] Step 102: Collect call data during the call.

[0037] During the call, call data is collected for subsequent analysis.

[0038] Step 103: During the call, the terminal and call data are detected based on the first risk score to obtain the second risk score.

[0039] After an audio / video call is established, the real-time monitoring unit continues to operate, and the second monitoring indicator includes: Terminal resource data, such as CPU utilization and memory utilization; Audio and video quality data, such as audio MOS (Mean Opinion Score), video MOS, first frame time, and number of stutters; Recording status data, such as recording start status, writing status, interruption status, and writing delay; Business recognition data, such as face status, liveness status, sensitive word status, speech recognition status, and text recognition status.

[0040] In one embodiment, during a call, based on a first risk score, the terminal and call data are inspected to obtain a second risk score, including: If the first risk score is greater than the first preset threshold, then the first indicator whose abnormal score is greater than the second preset threshold is determined as the target first indicator. During the call, identify the second target indicator that corresponds to the first target indicator in the terminal and call data; The sampling period of the second indicator in the terminal and call data is adjusted, as are the preset threshold and level of abnormality corresponding to the target second indicator. Based on the adjusted data, all secondary indicators in the terminal and call data are examined to obtain a secondary risk score.

[0041] Specifically, when the first risk score exceeds the first preset threshold, it indicates that the call should no longer be monitored according to the default strategy, but should enter a high-priority monitoring mode. The linkage control unit generates a PrecheckResult message, adding high-risk anomalies (the first indicator with an anomaly score exceeding the second preset threshold) to the key monitoring list. Simultaneously, a MonitorPolicyUpdate message is generated and sent to the in-process monitoring unit to adjust the sampling period of the second indicator, the preset threshold for the target second indicator, and the anomaly level. Through this mechanism, the pre-call phase no longer merely outputs a self-check report, but directly influences the monitoring intensity during the call.

[0042] The PrecheckResult message is an output message in the pre-call phase, which may include the call_id, terminal_type, first risk score, and event_id of the target first indicator for this call.

[0043] The MonitorPolicyUpdate message is a dynamic monitoring policy message sent during a call to update the monitoring policy. It can include the sampling period of the second indicator, the preset threshold for anomalies corresponding to the target second indicator, and the anomaly level.

[0044] The sampling period for the second indicator is, for example, 2 seconds / time under normal conditions. If an anomaly is detected before a call, the sampling period is adjusted to 200ms / time. The target first indicator is, for example, microphone access. If the microphone access score is greater than a second preset threshold during pre-call detection, it indicates an abnormality in microphone access. During the call, the second indicator for microphone access includes audio MOS. Under normal conditions, the preset threshold for audio MOS is, for example, 3.0, meaning an alarm is triggered only when it is less than 3.0. If an anomaly is detected before a call, the preset threshold for audio MOS is adjusted to 3.5, meaning an alarm is triggered when it is less than 3.5. The anomaly level can be divided into low-risk, medium-risk, and high-risk levels. Under normal conditions, an audio MOS less than 3.0 corresponds to a medium-risk level. If an anomaly is detected before a call, the anomaly level corresponding to an audio MOS less than 3.0 is adjusted to a high-risk level.

[0045] By adjusting the sampling period of the second indicator, the preset threshold for anomalies corresponding to the target second indicator, and the anomaly level, all second indicators in the terminal and call data are detected to obtain a second risk score.

[0046] Specifically, the linkage control unit generates a second risk score based on the aforementioned second indicator, which can be obtained through weighted fusion, rule engine, or model engine.

[0047] Step 104: After the call ends, determine the quality inspection intensity score based on the first risk score and the second risk score.

[0048] In one embodiment, after the call ends, a quality inspection intensity score is determined based on a first risk score and a second risk score, including: Determine the linkage penalty factor and its corresponding weight; Determine the weights corresponding to the first risk score and the second risk score, respectively; The quality inspection intensity score is determined by summing the products of the first risk score, the second risk score, and the linkage penalty factor with their respective weights.

[0049] Specifically, the linkage control unit combines the first risk score, the second risk score, and the linkage penalty factor to calculate the quality inspection intensity score:

[0050] in, To score the quality inspection intensity, As the first risk score, For the second risk score, As a linkage penalty factor, , and These are the weights of the first risk score, the second risk score, and the associated penalty factor, respectively.

[0051] The linkage penalty factor is used to increase the quality inspection intensity score and increase the quality inspection intensity in the post-call stage when serious problems such as abnormal recording status, business abnormality, or server abnormality occur.

[0052] Among them, abnormal recording status includes problems such as recording failure, interrupted recording, file corruption, writing failure, and excessive recording delay; abnormal business includes problems such as liveness detection failure, no face detected, sensitive word detection, violation of regulations, and non-standard business processes; abnormal server-side issues include problems such as server timeout, node failure, link interruption, and service unavailability.

[0053] In this embodiment, the call-in-process phase is responsible not only for real-time monitoring and alarms, but also directly determines the quality inspection intensity and template after the call ends.

[0054] Step 105: Based on the quality inspection intensity score, perform quality inspection on the call data and obtain the quality inspection results.

[0055] In one embodiment, the quality inspection intensity score is divided into a first interval, a second interval, and a third interval in ascending order. Each interval corresponds to a different intensity of quality inspection. The higher the quality inspection intensity score, the greater the corresponding quality inspection intensity. Based on the quality inspection intensity score, the call data is inspected to obtain the inspection results, including: In response to the quality inspection intensity score being in the first range, the call data will be subject to the first level of quality inspection. In response to the quality inspection intensity score being in the second range, the call data will be subject to the second level of quality inspection. In response to the quality inspection intensity score being in the third range, the call data will be subject to the third level of quality inspection. Based on the first, second, or third level of quality inspection, identify any abnormalities in the call data.

[0056] Specifically, the quality inspection intensity score, ranging from 0 to 1, can be divided into three intervals: the first interval, the second interval, and the third interval. For example, the quality inspection intensity score for the first interval can be less than or equal to 0.3, the quality inspection intensity score for the second interval can be greater than 0.3 and less than or equal to 0.8, and the quality inspection intensity score for the third interval can be greater than 0.8. Each interval corresponds to a different level of quality inspection intensity, with higher scores indicating greater inspection intensity. Thus, post-call quality inspection is not performed uniformly across all calls, but rather in tiers based on intensity, balancing cost and effectiveness.

[0057] When the quality inspection intensity score is in the first range, the call data is subjected to the first intensity of quality inspection. The first intensity of quality inspection is the basic quality inspection task, which includes media layer inspection. The media layer inspection includes indicators such as file integrity, audio and video track alignment, stuttering rate, empty frame ratio, human voice ratio, and signal-to-noise ratio.

[0058] When the quality inspection intensity score is in the second range, the call data is subjected to a second-intensity quality inspection. The second-intensity quality inspection is an enhanced quality inspection task, which includes media layer detection, speech transcription detection, and semantic quality detection. Among them, speech transcription detection is to detect whether the voice content in the recorded file can be converted into searchable text; semantic quality detection is to detect standardized language, sensitive words, risk warnings, service attitude, or problem-solving level, etc., according to the business rule base.

[0059] When the quality inspection intensity score is in the third range, the call data is subjected to the third intensity of quality inspection. The third intensity of quality inspection is a special composite task, which includes not only media layer detection, speech transcription detection and semantic quality detection, but also calling the specified industry rule base and focusing on reviewing abnormal indicators.

[0060] In this embodiment of the disclosure, by detecting terminal indicators before the call, conducting real-time monitoring based on the previous detection results during the call, and determining the quality inspection intensity score and performing corresponding quality inspections after the call by combining the detection results of the first two stages, it is possible to achieve quality inspection of audio and video calls throughout their entire lifecycle. This effectively solves the problem of independent quality inspection stages and fragmented data in the prior art. The detection results of each stage are interconnected and work synergistically, which can significantly improve the accuracy and comprehensiveness of anomaly detection and reduce the probability of missed detections and false detections.

[0061] In one embodiment, after determining the anomaly present in the call data, the method further includes: For each abnormal issue in the call data, at least one root cause score is calculated according to the root cause scoring formula. The root cause corresponding to the highest root cause score is identified as the primary root cause of the abnormal problem.

[0062] In one embodiment, for each anomalous issue in the call data, at least one root cause score is calculated according to the root cause scoring formula, including: The root cause scoring formula is shown below:

[0063] in, Root cause scoring, To determine the relevance of this anomaly before and during the call, To determine the relevance of this anomaly during and after the call, To determine the severity of this anomaly, , , They are respectively , and The weight.

[0064] Specifically, the data aggregation and tracing unit acquires event data from each stage—before, during, and after the call—and constructs a causal chain based on `call_id` and `trace_parent_id`. This causal chain is a path that connects events across multiple stages according to their time and relationships. For example, in the scenario of abnormal camera permissions leading to high first-frame latency, low video MOS value, and high stuttering rate, the abnormal camera permissions occur before the call and are the root cause of the entire causal chain. High first-frame latency occurs at the beginning of the call and is the first quality issue caused by abnormal camera permissions. Low video MOS value occurs during the call and is a continuation of high first-frame latency, also an indirect core issue caused by abnormal camera permissions. High stuttering rate is present in both the call and call termination stages and is the final result of the entire causal chain.

[0065] For each abnormal issue, there may be multiple causal chains. For example, the root cause of high screen stuttering rate may not only be abnormal camera permissions, but also unstable network status. Two root causes will correspond to two causal chains.

[0066] For each anomaly, the linkage control unit calculates the root cause score for at least one causal chain corresponding to each anomaly using the root cause scoring formula. The root cause corresponding to the causal chain with the highest root cause score is identified as the primary root cause of the anomaly, while other root causes are output as secondary causes. The final generated TraceReport message includes at least the primary root cause, the causal path, the confidence level, and handling recommendations. In this way, the system can structurally express cross-stage problem paths such as "abnormal camera permissions on a certain terminal lead to video quality degradation, which in turn causes abnormal subsequent recordings."

[0067] In this embodiment, the pre-inspection unit, the in-process monitoring unit, the post-inspection quality control unit, and the linkage control unit communicate through a unified interaction protocol. This protocol can use JSON, Protobuf, or other structured encoding / decoding methods to carry the message body. Examples include the aforementioned PrecheckResult message and MonitorPolicyUpdate message.

[0068] In addition to the business fields, the protocol message can also include a version number, signature field, idempotency identifier, terminal capability description field, and compatibility field to ensure protocol compatibility between different terminals, different versions of clients and servers.

[0069] In this embodiment of the disclosure, the protocol messages are standardized and can be reused when deployed on different systems and terminals, without the need for repeated development.

[0070] This disclosure also provides an audio / video call quality detection device. Figure 2 This is a schematic diagram of the audio / video call quality detection device provided in the embodiments of this disclosure, as shown below. Figure 2 As shown, the device includes: The first quality inspection unit 201 is used to detect multiple first indicators of the terminal before the call to obtain a first risk score; The acquisition unit 202 is used to acquire call data during a call. The second quality inspection unit 203 is used to inspect the terminal and call data during the call based on the first risk score to obtain the second risk score. The third quality inspection unit 204 is used to determine the quality inspection intensity score based on the first risk score and the second risk score after the call ends. The fourth quality inspection unit 205 is used to perform quality inspection on the call data based on the quality inspection intensity score and obtain the quality inspection result.

[0071] The specific details of each part of the above-mentioned device have been described in detail in the method section of the implementation plan. For any undisclosed details, please refer to the implementation plan of the method section, and therefore will not be repeated here.

[0072] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0073] Figure 3 A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0074] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0075] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0076] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as the audio and video call quality detection method. For example, in some embodiments, the audio and video call quality detection method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the audio and video call quality detection method described above can be performed. Alternatively, in other embodiments, the computing unit 301 can be configured to perform the audio and video call quality detection method by any other suitable means (e.g., by means of firmware).

[0077] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0078] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0079] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0080] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0081] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0082] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0083] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0084] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise explicitly specified.

[0085] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for detecting audio and video call quality, characterized in that, The method includes: Before the call, several primary indicators of the terminal are tested to obtain a primary risk score; Collect call data during the call process; During the call, based on the first risk score, the terminal and the call data are detected to obtain a second risk score; After the call ends, a quality inspection intensity score is determined based on the first risk score and the second risk score. The call data is inspected based on the quality inspection intensity score to obtain the quality inspection result.

2. The method according to claim 1, characterized in that, Before the call, several primary indicators of the terminal are detected to obtain a primary risk score, including: Before the call, identify any abnormal scores for each primary metric; Based on the abnormal scores of each primary indicator and the corresponding weight of each primary indicator, the risk score of each primary indicator is determined. The first risk score is determined by summing the risk scores of all first indicators.

3. The method according to claim 2, characterized in that, During the call, based on the first risk score, the terminal and the call data are detected to obtain a second risk score, including: If the first risk score is greater than the first preset threshold, then the first indicator whose abnormal score is greater than the second preset threshold is determined as the target first indicator. During the call, a second target indicator corresponding to the first target indicator is determined in the terminal and the call data; The sampling period of the second indicator in the terminal and the call data is adjusted, as are the abnormal preset threshold and abnormal level corresponding to the target second indicator; Based on the adjusted data, all second indicators in the terminal and the call data are detected to obtain a second risk score.

4. The method according to claim 1, characterized in that, After the call ends, the quality inspection intensity score is determined based on the first risk score and the second risk score, including: Determine the linkage penalty factor and its corresponding weight; Determine the weights corresponding to the first risk score and the second risk score, respectively; The quality inspection intensity score is determined by summing the products of the first risk score, the second risk score, and the linkage penalty factor with their respective weights.

5. The method according to claim 1, characterized in that, The quality inspection intensity score is divided into three intervals from smallest to largest: the first interval, the second interval, and the third interval. Each interval corresponds to a different intensity of quality inspection. The higher the quality inspection intensity score, the greater the corresponding quality inspection intensity. The step of performing quality inspection on the call data based on the quality inspection intensity score to obtain the quality inspection result includes: In response to the quality inspection intensity score being in the first range, the call data is subjected to a quality inspection of the first intensity. In response to the quality inspection intensity score being in the second range, the call data is subjected to a second intensity of quality inspection; In response to the quality inspection intensity score being in the third interval, the call data is subjected to a third-intensity quality inspection; Based on the quality inspection of the first intensity, the second intensity, or the third intensity, anomalies in the call data are determined.

6. The method according to claim 5, characterized in that, After identifying the anomalies in the call data, the method further includes: For each abnormal issue in the call data, at least one root cause score is calculated according to the root cause scoring formula; The root cause corresponding to the highest root cause score is identified as the primary root cause of the abnormal problem.

7. The method according to claim 6, characterized in that, For each anomalous issue in the call data, at least one root cause score is calculated according to the root cause scoring formula, including: The root cause scoring formula is as follows: in, Root cause scoring, To determine the relevance of this anomaly before and during the call, To determine the relevance of this anomaly during and after the call, To determine the severity of this anomaly, , , They are respectively , and The weight.

8. An audio / video call quality detection device, characterized in that, The device includes: The first quality inspection unit is used to test multiple primary indicators of the terminal before a call to obtain a primary risk score. The data acquisition unit is used to collect call data during the call process; The second quality inspection unit is used to inspect the terminal and the call data during the call based on the first risk score to obtain a second risk score. The third quality inspection unit is used to determine the quality inspection intensity score based on the first risk score and the second risk score after the call ends. The fourth quality inspection unit is used to perform quality inspection on the call data based on the quality inspection intensity score, and obtain the quality inspection result.

9. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

Images