Double-recording quality inspection method and device, storage medium and computer program product

Abstract

The invention discloses a double-recording quality inspection method and device, a storage medium and a computer program product, and relates to the technical field of big data and artificial intelligence, and the double-recording quality inspection method comprises the steps: obtaining a target media stream in response to a media stream request; performing quality inspection analysis on the target media stream; and outputting alarm information under the condition that quality inspection analysis has an error. According to the method and the device, quality inspection analysis is performed on the media stream data in real time while recording is performed, and the alarm information is fed back to the client under the condition that a potential problem is found, so that real-time feedback of the potential problem of the dual-recording video data is realized.

Description

Technical Field

[0001] The present application relates to the technical field of big data and artificial intelligence, and in particular to a double-recording quality inspection method, device, storage medium and computer program product. Background Art

[0002] With the advancement of information technology, the dual recording system has gradually integrated advanced technologies such as digitization and networking, realizing digital storage and remote access of recorded files. In recent years, with the rapid development of technologies such as artificial intelligence and big data, the dual recording system has begun to have more complex analysis functions, such as voice recognition and image recognition, providing a more convenient and efficient tool for quality inspection.

[0003] In conventional technology, traditional double-recording quality inspection is usually performed offline after the recording is completed. This method has obvious lags, which not only makes it impossible to identify risks such as misleading and fraud in a timely manner, but also may cause financial losses to customers. In addition, if the quality inspection results do not meet regulatory requirements, this lag requires users to start the re-recording process, which consumes a lot of resources and increases customers' time costs.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a dual-recording quality inspection method, device, storage medium and computer program product, aiming to solve the technical problem of lagging feedback on dual-recording video problems.

[0006] To achieve the above purpose, the present application proposes a double recording quality inspection method, the method comprising: In response to the media stream request, obtaining a target media stream; Performing quality inspection and analysis on the target media stream; In the event that an error occurs in the quality inspection analysis, an alarm message is output.

[0007] In one embodiment, the method is applied to a dual-recording quality inspection device, the dual-recording quality inspection device includes a multimedia gateway and a quality inspection service center, and before the step of performing quality inspection and analysis on the target media stream, further includes: Based on the real-time streaming protocol RTSP, a real-time data stream channel is established between the multimedia gateway and the quality inspection service center; The target media stream is sent to the quality inspection service center through the multimedia gateway based on the real-time data stream channel, wherein the quality inspection service center is used to perform quality inspection and analysis on the media stream.

[0008] In one embodiment, before the step of sending the target media stream to the quality inspection service center through the multimedia gateway based on the real-time data stream channel, the step further includes: Verifying the source client of the media stream request according to the authority information of the source client through the multimedia gateway; If the verification is passed, the step of sending the target media stream to the quality inspection service center is performed.

[0009] In one embodiment, the step of performing quality inspection and analysis on the media stream includes: Determine whether the waiting time of the audio and video frames of the media stream exceeds a preset time threshold; When the waiting time of the audio and video frames exceeds the time threshold, reading the historical frames of the audio and video frames, and judging whether the transmission of the media stream is stuck according to the historical frames of the audio and video frames; In the case where the transmission of the media stream is stuck, it is determined that an error occurs in the quality inspection analysis.

[0010] In one embodiment, the step of performing quality inspection and analysis on the media stream includes: Using natural language processing technology, extracting keywords from the audio data of the media stream, and comparing them with a preset sensitive word library; In the case where at least one of the keywords belongs to the preset sensitive word library, it is determined that an error occurs in the quality inspection analysis.

[0011] In one embodiment, the step of performing quality inspection and analysis on the media stream includes: Using face recognition technology to determine the identity of a human target in the video data of the media stream; In the case that at least one of the portrait targets is not fully displayed, and / or the identity of at least one of the portrait targets does not belong to a preset security identity library, it is determined that an error occurs in the quality inspection analysis.

[0012] In one embodiment, the step of performing quality inspection and analysis on the media stream includes: Using a computer vision analysis algorithm, by analyzing the facial expressions and movements of the portrait target, the behavioral intention of the portrait target is determined; In the case where there is at least one behavior intention that belongs to the preset abnormal behavior library, it is determined that an error occurs in the quality inspection analysis.

[0013] In addition, to achieve the above purpose, the present application also proposes a dual recording quality inspection device, the dual recording quality inspection device comprising: An acquisition module, used for acquiring a target media stream in response to a media stream request; A quality inspection module, used for performing quality inspection and analysis on the target media stream; The alarm module is used to output an alarm message when an error occurs in the quality inspection analysis.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a dual recording quality inspection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the dual recording quality inspection method described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the double recording quality inspection method described above are implemented.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the double recording quality inspection method as described above.

[0017] One or more technical solutions proposed in the present application have at least the following technical effects: in response to a media stream request, a target media stream is obtained. This automated media stream pulling process reduces the steps of manual screening and can switch between different conferences for viewing and analysis in real time according to the user's media stream request, thereby realizing dynamic monitoring of dual-recording video data; after obtaining the required media stream, a quality inspection and analysis is performed on the target media stream to realize real-time monitoring and analysis of the media stream so as to timely discover potential business problems; and in the event of errors in the quality inspection and analysis, an alarm message can be output to remind the user to check and remedy the potential problems, thereby realizing real-time feedback on potential problems so that staff can deal with related problems in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart of the first embodiment of the double recording quality inspection method of this application is provided; Figure 2A schematic diagram of the feedback direction of the quality inspection results provided in Example 1 of the present application; Figure 3 A schematic diagram of the structure of a data stream channel at a transmitting end provided in Embodiment 1 of the present application; Figure 4 An interactive diagram of the authentication process provided in Example 1 of the present application; Figure 5 A schematic diagram of the process of jamming identification and processing provided in the second embodiment of the present application; Figure 6 A schematic diagram of the overall process of the dual recording quality inspection method provided in Example 2 of the present application; Figure 7 This is a schematic diagram of the module structure of the dual-recording quality inspection device according to an embodiment of the present application; Figure 8 Schematic diagram of the device structure of the hardware operating environment involved in the dual recording quality inspection method in the embodiment of the present application. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] In this embodiment, for ease of description, the following description is made with the dual-recording quality inspection device as the execution subject.

[0024] In conventional technology, the dual recording system has realized the digital storage of recording files, making data management and access more convenient. The remote access function allows relevant personnel to view and analyze dual recording files anytime and anywhere, improving work efficiency. However, this quality inspection and analysis is carried out after the recording is completed. Relevant personnel cannot deal with any problems in a timely manner and can only allow losses to occur or re-record afterwards.

[0025] The present application provides a solution, which responds to a media stream request and obtains a target media stream, thereby reducing the manual screening process and improving the quality inspection efficiency; after obtaining the required media stream, based on the real-time streaming protocol RTSP, the media stream is sent to a quality inspection service center, thereby realizing real-time transmission of media stream data; and quality inspection and analysis are performed on the media stream, including identifying freezes by monitoring waiting time, extracting audio keywords for speech detection, extracting facial features for identity verification, extracting action features for behavior detection, etc., so as to promptly detect illegal operations of the recorded personnel and identify potential business problems; and then, in the event of an error in the quality inspection analysis, an alarm message is sent to the client, thereby solving the problem after the problem feedback and realizing real-time feedback of potential problems, so that the staff can deal with related problems in a timely manner, avoid unnecessary re-recording operations, and reduce resource waste.

[0026] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes the dual recording quality inspection device as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0027] Based on this, the present application embodiment provides a dual recording quality inspection method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the double recording quality inspection method of the present application.

[0028] In this embodiment, the dual recording quality inspection method includes steps S10 to S30: Step S10, in response to the media stream request, obtaining the target media stream; It should be noted that a media stream request refers to a network request issued by a client to obtain certain media resources (such as audio and video). The media stream request may contain a series of data identifiers used to describe the characteristics of the meeting, including but not limited to meeting parameters such as the meeting number and the identifiers of the participants in the meeting. Therefore, the network address of the target media stream can be determined based on the meeting parameters. The network address refers to the identifier used to identify the location of the media resource in the network.

[0029] In addition, it should be noted that media stream refers to continuous audio, video or other multimedia data transmitted in the network. These data are sent in the form of continuous data packets, and the receiving end reassembles these data packets into continuous media content. Acquisition refers to the process of the multimedia gateway actively acquiring the media stream from the source, and establishing a connection with the media cloud through specific protocols and methods, such as RTSP (Real Time Streaming Protocol), RTMP (Real Time Messaging Protocol), etc., and then the audio and video media streams provided by the media cloud can be obtained through the connection.

[0030] For example, if you want to perform real-time quality inspection on the current meeting, obtain the meeting number or participant information of the current meeting, and provide it to the multimedia gateway. The multimedia gateway searches for the corresponding media stream address based on the received message, uses the RTSP protocol to establish a connection with the media cloud, and pulls the corresponding target media stream data from the media cloud.

[0031] It is understandable that through the automated pulling process, manual intervention is reduced and unnecessary waiting time for quality inspection and analysis is reduced.

[0032] Step S20, performing quality inspection and analysis on the target media stream; For example, the current conference media stream of customer A and service personnel B is pulled through the multimedia gateway, and the media stream is transmitted in real time to the quality inspection service center through RTSP and RTP (Real-time Transport Protocol); after the quality inspection service center receives the media stream, it can authenticate the identities of the participants to ensure that no irrelevant personnel participate in the meeting and ensure the reliability of the business process; it can also check the quality of audio and video to ensure customer experience.

[0033] It can be understood that by sending the media stream to the quality inspection service center and using the center for quality inspection and analysis, the quality control and compliance of the media stream are effectively improved, thereby ensuring the clarity and reliability of communication, while reducing operational risks and improving the overall service quality.

[0034] Step S30: if an error occurs in the quality inspection analysis, an alarm message is output.

[0035] It should be noted that an error refers to a situation in which the media stream does not meet the audio and video quality standards during the quality inspection and analysis process; an alarm message is a notification provided by the Quality Service Center to notify the user or system that a problem has occurred in the meeting corresponding to the current media stream and that it needs to be processed as soon as possible. The alarm message may include the error type, timestamp, recommended operations, etc.

[0036] Exemplarily, face recognition technology is used to authenticate the identities of meeting participants. If face recognition is incomplete, or the recognized face does not match the recorded meeting participants, an alarm message is generated and sent to the client so that quality inspectors can handle or remedy the situation in a timely manner.

[0037] For example, please refer to Figure 2 , Figure 2 A schematic diagram of the judgment directions for different quality inspection results is provided. During the process of executing step E101 to perform quality inspection and analysis on the media stream, it is determined whether an error occurs in the quality inspection and analysis. If no error occurs in the quality inspection and analysis, step E102 is executed to generate a quality inspection report and store it. If the quality inspection result is abnormal (an error occurs in the quality inspection and analysis), that is, a potential problem of the dual-recording conference is discovered, step E103 is executed to send an alarm message to the quality inspector through the conference control message channel, so that the quality inspector can remedy the problem in a timely manner.

[0038] This embodiment provides a dual-recording quality inspection method, which transmits the media stream to the quality inspection service center in real time. In the event of an error, a real-time response is triggered to notify the client or customer to handle it, thereby achieving real-time feedback on dual-recording video errors and avoiding delayed feedback on dual-recording video problems, which makes it too late to remedy the situation.

[0039] In a feasible implementation manner, the dual recording quality inspection method is applied to a dual recording quality inspection device, the dual recording quality inspection device includes a multimedia gateway and a quality inspection service center, and before step S20, further includes: Step S21, building a real-time data stream channel between the multimedia gateway and the quality inspection service center based on the real-time streaming protocol RTSP; It should be noted that RTSP is a network control protocol used to control the transmission of streaming media data. RTSP itself does not transmit streaming media data, but uses RTP and RTCP (Real-time Transport Control Protocol) to transmit data and control information. A real-time data stream channel refers to a channel established through the RTSP protocol for transmitting streaming media data, which ensures that streaming media data can be transmitted from the data source to the destination in real time and continuously. It can be actively established by the multimedia gateway based on the media stream request, or by the quality inspection service center when sending the media stream request. This implementation does not make specific restrictions on this.

[0040] In addition, it should be noted that a multimedia gateway refers to a network device responsible for processing and forwarding media streams, and is used to control access to media streams; a quality inspection service center refers to a server or server cluster used to receive, process and analyze media streams, and uses specific algorithms and rules to perform quality inspections on media streams, including but not limited to audio clarity, video fluency, content compliance, etc.

[0041] For example, please refer to Figure 3 , Figure 3 The invention provides a structural diagram of a data stream channel constructed by a transmitter based on the RTSP protocol. The application layer encapsulation can be divided into two parts, a control part 100 and a data part 200. The control part 100 can include RTSP101 and RTCP102. RTSP101 is responsible for encapsulating control instructions into data packets, which are mainly used for streaming media control, such as play, pause, etc. RTCP102 can provide encapsulation of control information, such as data transmission quality, participant identity, etc. The data part 200 includes RTP103, which is responsible for encapsulating media stream data. The cooperation of these protocols realizes the real-time transmission and control of media stream data. The transport layer mainly includes TCP104 and UDP105. TCP104 is responsible for further encapsulating the data packets encapsulated by RTSP101 into data packets of the transport layer. Since real-time data transmission has high requirements for delay and jitter, UDP105 is selected to further encapsulate the data packets encapsulated by RTCP102 and RTP103 into data packets of the transport layer, which can effectively reduce transmission delay and jitter. The network layer includes network protocol 107, which is responsible for data routing and forwarding, supports both IPv4 and IPv6 protocols, and further encapsulates the data packets of the transport layer into data packets of the network layer, which can then be transmitted over the network.

[0042] Exemplarily, each protocol is rebuilt using the Netty framework. Based on the low latency and high concurrency capabilities of the Netty framework, network jitter and latency can be effectively reduced while processing multiple data at the same time. Other underlying network communication frameworks, such as Twisted, Mina, etc., can also be used, which also support high-performance network applications. This implementation does not specifically limit the underlying framework used.

[0043] Step S22: sending the target media stream to the quality inspection service center through the multimedia gateway based on the real-time data stream channel, wherein the quality inspection service center is used to perform quality inspection and analysis on the media stream.

[0044] For example, during the discussion between the consultant and the client about the financial plan, the real-time data stream channel established by the RTSP protocol is used to send the captured audio and video data (media stream) to the quality inspection service center in real time through the multimedia gateway, so that the quality inspection service center can analyze the media stream in real time to ensure that there are no problems such as sound interruption or video occlusion during the communication process. If a problem is detected, the relevant personnel are notified immediately to intervene to ensure the quality and compliance of the discussion process.

[0045] In this embodiment, the real-time data stream channel constructed through the RTSP protocol can ensure the real-time transmission of media stream data, so that the quality inspection service center can receive and process data in real time, improve the response speed, thereby promptly discovering quality problems and sending alarm information to quality inspectors so that they can handle them in time.

[0046] In a feasible implementation manner, before step S22, the method further includes: Step E10, verifying the source client according to the authority information of the source client of the media stream request through the multimedia gateway; It should be noted that the permission information refers to the authentication information added to the current media stream request based on a preset rule according to the client's identity and media stream address, and is used to verify whether the client has the right to access specific media stream resources.

[0047] For example, when a user wants to perform real-time quality inspection on a current conference, the network address of the media stream is determined according to the user's request information, and permission information is generated according to the user's identity information, and the address and permission information are sent to the client.

[0048] Step E20: If the verification is passed, the target media stream is sent to the quality inspection service center.

[0049] For example, please refer to Figure 4 , Figure 4A flowchart of an authentication mechanism is provided, wherein the client executes step S101 to request a media stream address from a conference control, wherein the conference control refers to a management center of a dual-recording conference and has functions such as conference creation and conference recording, and the network request contains conference identification information such as the conference name; after receiving the network request, the conference control first finds the corresponding media stream address according to the conference name, and then generates permission information according to the identity information of the client and the media stream address (step S102), and executes step S103 to return the permission information and the media stream address to the client; the client executes step S104 to send the permission information and the media stream address to a quality inspection service center, and notifies the quality inspection service center to start quality inspection analysis; after receiving the quality inspection analysis instruction, the quality inspection service center executes step S105 to request a media stream from a multimedia gateway; the multimedia gateway performs permission verification (step S106), checks the permission information according to the identity of the client, and if the verification passes, executes step S107 to transmit the corresponding media stream to the quality inspection service center, so that the quality inspection service center performs quality inspection analysis on the media stream.

[0050] In this implementation, by verifying the permission information, it can be ensured that only legal and compliant clients can access specific media resources, thereby ensuring the security of dual-recording video data during transmission.

[0051] In a feasible implementation, the double recording quality inspection method includes: Step E30, encrypting the media stream, the request information and the response information, wherein the request information and the response information are generated during the process of pulling and transmitting the media stream.

[0052] It should be noted that request information refers to the request data sent by the client to the server during the process of pulling and transmitting the media stream, which is used to instruct the server to send the required media stream content; response information refers to the data packet containing media stream data or other related information returned to the client by the server after receiving the client's request information.

[0053] For example, please refer to Figure 4 , Figure 4 The conference identification information contained in step S101, the media stream address information and permission information transmitted in S104 and S105 can be regarded as request information, and the media stream address and permission information returned in step S103 can be regarded as response information. During the network transmission of request information, response information and media streams, symmetric encryption algorithms with higher security such as AES (Advanced Encryption Standard) or asymmetric encryption algorithms such as RSA (Rivest-Shamir-Adleman) can be used for encryption to improve the security of data during transmission.

[0054] In this implementation, plaintext data is converted into ciphertext data through encryption, thereby protecting the confidentiality and integrity of the media stream data and preventing unauthorized access or tampering.

[0055] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. On this basis, the step of performing quality inspection and analysis on the media stream in step S20 includes: Step S23, determining whether the waiting time of the audio and video frames of the media stream exceeds a preset time threshold; It should be noted that the audio and video frame refers to the basic unit of the media stream, and each audio and video frame contains a moment of audio or video data; the waiting time refers to the time it takes for the audio and video frame of the media stream to arrive at the current device and wait for the next frame to arrive. The preset time threshold is used to determine whether the waiting time for the audio and video frame is too long. If the waiting time exceeds the time threshold, it means that the next frame is delayed, and it is necessary to determine whether the transmission of the media stream has been stuck or the transmission has been terminated.

[0056] Step S24, when the waiting time of the audio and video frames exceeds the time threshold, reading the historical frames of the audio and video frames, and judging whether the transmission of the media stream is stuck according to the historical frames of the audio and video frames; It should be noted that the historical frame refers to the previously transmitted audio and video frame, and its timestamp and content information can be used to analyze the transmission of the current audio and video frame. The historical frame can be the previous frame or the previous frames, and can be adjusted according to the length of the waiting time, which is not specifically limited in this embodiment.

[0057] According to the historical frames of the audio and video frames, it is determined whether the transmission of the media stream is stuck. This step can be implemented by detecting whether the audio and video images stop to determine whether a stuck occurs.

[0058] Exemplarily, the dual-recording quality inspection equipment includes a multimedia gateway and a quality inspection service center. Since the time interval between audio and video frames is fixed, the time interval can be set as a time threshold. When the audio and video frame arrives at the multimedia gateway, the waiting time exceeds the time threshold. The multimedia gateway reads the previous frame of the current audio and video frame, and encapsulates the frame and sends it to the quality inspection service center. The quality inspection service center detects that the picture stops and determines that there is a freeze problem in the transmission of the media stream.

[0059] For example, when the waiting time of a certain audio or video frame exceeds the preset time threshold, the buffer of the audio or video frame is traced back, the historical data of the frame and several frames before it are read, and the change of the inter-frame delay is analyzed to determine whether the video stream is stuck. If the inter-frame delay is found to be irregular, with some frames having long intervals and others having short intervals, this indicates that the transmission of the media stream has been stuck.

[0060] Step S25: when the transmission of the media stream is stuck, it is determined that an error occurs in the quality inspection analysis.

[0061] For example, please refer to Figure 5 , Figure 5 A method for identifying and processing jams is provided. After receiving the media stream, the multimedia gateway puts it into a buffer and waits for the next step of processing. The audio and video frames in the buffer are read in the order of reception to determine whether the waiting time of the currently read audio and video frame exceeds the time threshold. If the waiting time of the current audio and video frame does not exceed the time threshold, the current frame is directly RTP encapsulated, and after encapsulation, it can be transmitted in the network and transmitted to the quality inspection service center for other quality inspection and analysis. If the waiting time of the current audio and video frame exceeds the time threshold, the previous frame of the current audio and video frame is read through the backtracking buffer, and the previous frame is used to fill the instantaneous gap. The previous frame is RTP encapsulated for network transmission. After receiving the frame, the quality inspection service center finds that the picture has not changed compared with the previous frame, determines that an error has occurred in the quality inspection analysis, and sends an alarm message to the quality inspector so that he can investigate and correct the cause of the error.

[0062] In this embodiment, by monitoring the waiting time of audio and video frames in real time and judging the transmission status based on historical frame data, the jamming problem in media stream transmission can be discovered and solved in time.

[0063] In a feasible implementation manner, the step of performing quality inspection and analysis on the media stream in step S20 includes: Step A10, using natural language processing technology to extract keywords from the audio data of the media stream, and compare them with a preset sensitive word library; It should be noted that Natural Language Processing (NLP) technology is a collection of algorithms and models used to understand and process human natural language (including text and speech), such as the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm and the TextRank algorithm. It can identify the keywords that best represent the content of a document by evaluating the importance of words in a document set.

[0064] For example, before extracting keywords, the audio data can be preprocessed, including noise reduction, voice enhancement, etc., to improve the accuracy of keyword extraction, and then the keyword extraction algorithm in NLP technology is used to identify and extract keywords from the preprocessed audio data, and the extracted keywords are compared with the words in the sensitive word library one by one, and the matching results are recorded. If there is a match, it means that there is an illegal expression, and subsequent processing is performed according to the preset rules, such as issuing a warning, filtering content, etc.

[0065] Step A20: When there is at least one keyword belonging to the preset sensitive word library, it is determined that an error occurs in the quality inspection analysis.

[0066] For example, during the sales process of financial products, quality inspection and analysis are performed on the recorded data of sales personnel and customers, and sensitive words such as "high return" and "capital preservation" are extracted using the TF-IDF algorithm. It is judged that errors may have occurred in the quality inspection and analysis, and the quality inspectors are reminded to conduct further inspection and processing.

[0067] In this implementation, by using NLP technology, keywords are automatically extracted and compared with a sensitive word library, which can greatly reduce the workload of manual monitoring and improve quality inspection efficiency.

[0068] In a feasible implementation manner, the step of performing quality inspection and analysis on the media stream in step S20 includes: Step A30, using face recognition technology to determine the identity of the portrait target in the video data of the media stream; It should be noted that face recognition technology refers to algorithms and models that can detect and identify faces from images or video frames, such as the Eigenface algorithm, convolutional neural networks, etc., which identify or verify the identity of an individual by analyzing facial features (such as facial contours, eyes, nose, mouth, etc.) in videos or images; portrait targets refer to individual faces captured by the camera and appearing in the video screen in the video data of the media stream.

[0069] Step A40: if at least one portrait target is not fully displayed and / or the identity of at least one portrait target does not belong to the preset security identity library, it is determined that an error occurs in the quality inspection analysis.

[0070] It should be noted that incomplete display means that the portrait target is not fully presented in the image or video frame data, which may be caused by image cropping, occlusion, screen distortion, etc. The preset safe identity library refers to a database that is pre-established and stores portrait target information that is considered safe and has known identities.

[0071] For example, when a salesperson is promoting a financial product to a customer, facial recognition technology is used to detect and identify faces in the video data of the media stream and compare them with the security identity database. If it is found that the face of a portrait target is obscured or the identity of a certain person is not in the security identity database, it is immediately determined that an error has occurred in the quality inspection analysis and security measures are taken, such as terminating the call or notifying the quality inspector.

[0072] In this embodiment, through face recognition technology, the identity of each portrait target in the video data of the media stream can be quickly and accurately determined, thereby improving the efficiency of quality inspection, ensuring the security of the business process, and achieving real-time feedback on quality inspection errors.

[0073] In a feasible implementation manner, the step of performing quality inspection and analysis on the media stream in step S20 includes: Step A50, using a computer vision analysis algorithm to analyze the facial expression and movements of the portrait target to determine the behavioral intention of the portrait target; It should be noted that computer vision analysis algorithm refers to an algorithm that uses image processing, pattern recognition, artificial intelligence and other technologies to automatically analyze and understand the content in images or videos, such as convolutional neural networks, recursive neural networks, etc.; behavioral intention refers to inferring the intention or purpose of the behavior that a person may want to perform or is performing by analyzing the expression, action and other features of the portrait target.

[0074] For example, a computer vision analysis algorithm is used to analyze the expressions and movements of a customer who is withdrawing money under surveillance. When a customer panics, looks around, and quickly enters his password, it can be determined that the customer's behavioral intention is "abnormal withdrawal," and the staff can be alerted to check and process it.

[0075] Step A60: When there is at least one behavior intention that belongs to the preset abnormal behavior library, it is determined that an error occurs in the quality inspection analysis.

[0076] It should be noted that the abnormal behavior library refers to a preset database containing various behaviors that are considered abnormal or non-compliant. It can be used as a "blacklist" that lists all behaviors that are not allowed or require vigilance.

[0077] For example, when a salesperson is introducing a financial product to a customer, a computer vision analysis algorithm is used to analyze the salesperson's facial expressions and movements to determine his or her behavioral intentions. If his or her behavioral intentions match the entries in the abnormal behavior library, it is immediately determined that an error has occurred in the quality inspection analysis and the quality inspector is notified to handle the issue.

[0078] In this implementation, the behavioral intentions of the portrait target are determined by analyzing their expressions and movements, which effectively improves the security and compliance of the media stream content. At the same time, when anomalies occur, real-time feedback is provided to the staff to avoid the accumulation of problems and delayed processing.

[0079] For example, in order to help understand the implementation process of the dual recording quality inspection method obtained by combining the above-mentioned embodiment 1 and embodiment 2, please refer to Figure 6 , Figure 6 A schematic diagram of the overall process of a double recording quality inspection method is provided, specifically: Step B101, the client 300 establishes an audio and video connection with the media cloud 400, and various operations such as play, pause, etc. can be directly performed on the audio and video through the client 300.

[0080] In step B102 , the client 300 notifies the dual recording device 500 to start recording, and the recorded audio and video data can be obtained by different devices through the media cloud 400 .

[0081] Step B103 , the client 300 notifies the multimedia gateway 600 to start real-time quality inspection, and the client 300 provides the multimedia gateway 600 with conference parameters.

[0082] In step B104, the dual recording device 500 and the multimedia gateway 600 pull corresponding media streams according to the conference parameters.

[0083] In step B105, the multimedia gateway 600 transmits the pulled media stream to the quality inspection service center 700 for quality inspection analysis, including freeze recognition, portrait detection, behavior detection, etc.

[0084] Step B106 : The quality inspection service center 700 feeds back the quality inspection result to the client 300 .

[0085] Step B107, the storage device 800 archives the recorded audio and video data.

[0086] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the double-recording quality inspection method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0087] This application also provides a dual recording quality inspection device, please refer to Figure 7 , the dual recording quality inspection device comprises: The acquisition module 10 is used to acquire the target media stream in response to the media stream request; The quality inspection module 20 is used to perform quality inspection and analysis on the target media stream; The alarm module 30 is used to output an alarm message when an error occurs in the quality inspection analysis.

[0088] The dual recording quality inspection device provided by the present application adopts the dual recording quality inspection method in the above embodiment, which can solve the technical problem of lag in the problem feedback of dual recording videos. Compared with the prior art, the beneficial effects of the dual recording quality inspection device provided by the present application are the same as the beneficial effects of the dual recording quality inspection method provided by the above embodiment, and the other technical features of the dual recording quality inspection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0089] The present application provides a dual recording quality inspection device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the dual recording quality inspection method in the above-mentioned embodiment one.

[0090] Reference below Figure 8 , which shows a schematic diagram of the structure of a dual recording quality inspection device suitable for implementing the embodiment of the present application. The dual recording quality inspection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The dual-recording quality inspection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0091] like Figure 8As shown, the dual recording quality inspection device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the dual recording quality inspection device are also stored in RAM1004. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the dual recording quality inspection device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a dual recording quality inspection device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0092] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0093] The dual recording quality inspection device provided by the present application adopts the dual recording quality inspection method in the above embodiment, which can solve the technical problem of lag in the feedback of the dual recording video. Compared with the prior art, the beneficial effects of the dual recording quality inspection device provided by the present application are the same as the beneficial effects of the dual recording quality inspection method provided by the above embodiment, and the other technical features of the dual recording quality inspection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0094] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0095] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0096] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the double-recording quality inspection method in the above-mentioned embodiment.

[0097] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0098] The computer-readable storage medium may be included in the dual-recording quality inspection device; or may exist independently without being assembled into the dual-recording quality inspection device.

[0099] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the dual-recording quality inspection device, the dual-recording quality inspection device: responds to the media stream request and obtains the target media stream; performs quality inspection and analysis on the target media stream; and outputs an alarm message when an error occurs in the quality inspection and analysis.

[0100] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0101] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0103] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned dual-recording quality inspection method, and can solve the technical problem that the feedback of the problem of dual-recording videos has a lag. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the dual-recording quality inspection method provided in the above-mentioned embodiment, and will not be elaborated here.

[0104] The present application also provides a computer program product, including a computer program, which implements the steps of the double-recording quality inspection method as described above when executed by a processor.

[0105] The computer program product provided by the present application can solve the technical problem that there is a lag in the feedback of the problem of double recording video. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the double recording quality inspection method provided by the above embodiment, which will not be repeated here.

[0106] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A double recording quality inspection method, characterized in that: The double recording quality inspection method comprises: In response to the media stream request, obtaining a target media stream; Performing quality inspection and analysis on the target media stream; In the event that an error occurs in the quality inspection analysis, an alarm message is output.

2. The dual recording quality inspection method according to claim 1, characterized in that: The method is applied to a dual-recording quality inspection device, the dual-recording quality inspection device includes a multimedia gateway and a quality inspection service center, and before the step of performing quality inspection and analysis on the target media stream, further includes: Based on the real-time streaming protocol RTSP, a real-time data stream channel is established between the multimedia gateway and the quality inspection service center; The target media stream is sent to the quality inspection service center through the multimedia gateway based on the real-time data stream channel, wherein the quality inspection service center is used to perform quality inspection and analysis on the target media stream.

3. The dual recording quality inspection method according to claim 2, characterized in that: Before the step of sending the target media stream to the quality inspection service center through the multimedia gateway based on the real-time data stream channel, the step further includes: Verifying the source client of the media stream request according to the authority information of the source client through the multimedia gateway; If the verification is passed, the step of sending the target media stream to the quality inspection service center is performed.

4. The dual recording quality inspection method according to claim 1, characterized in that: The step of performing quality inspection and analysis on the target media stream comprises: Determine whether the waiting time of the audio and video frames of the target media stream exceeds a preset time threshold; When the waiting time of the audio and video frames exceeds the time threshold, reading the historical frames of the audio and video frames, and judging whether the transmission of the target media stream is stuck according to the historical frames of the audio and video frames; In the case where the transmission of the target media stream is stuck, it is determined that an error occurs in the quality inspection analysis.

5. The dual recording quality inspection method according to claim 1, characterized in that: The step of performing quality inspection and analysis on the target media stream comprises: Using natural language processing technology, extracting keywords from the audio data of the target media stream, and comparing them with a preset sensitive word library; In the case where at least one of the keywords belongs to the preset sensitive word library, it is determined that an error occurs in the quality inspection analysis.

6. The dual recording quality inspection method according to claim 1, characterized in that: The step of performing quality inspection and analysis on the target media stream comprises: Using face recognition technology to determine the identity of a human target in the video data of the target media stream; In the case that at least one of the portrait targets is not fully displayed, and / or the identity of at least one of the portrait targets does not belong to a preset security identity library, it is determined that an error occurs in the quality inspection analysis.

7. The double recording quality inspection method according to claim 6, characterized in that: The step of performing quality inspection and analysis on the target media stream comprises: Using a computer vision analysis algorithm, by analyzing the facial expressions and movements of the portrait target, the behavioral intention of the portrait target is determined; In the case where there is at least one behavior intention that belongs to the preset abnormal behavior library, it is determined that an error occurs in the quality inspection analysis.

8. A dual-recording quality inspection device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the double-recording quality inspection method according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the double-recording quality inspection method according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the double recording quality inspection method according to any one of claims 1 to 7 are implemented.

Images