Data processing method and device, computer device, storage medium and program product

Abstract

The application provides a data processing method and device, computer equipment, a storage medium and a program product, relates to the live broadcast field, and can be applied to a live broadcast scene. The data processing method comprises the following steps: receiving an identification log generated based on at least one live broadcast video stream of at least one live broadcast user in at least one time period and sent by an identification terminal; the identification terminal is also used for generating a corresponding identification label based on the live broadcast video stream, and sending the identification label to a corresponding live broadcast room for display; receiving query information sent by a query terminal; the query information comprises a target user identifier and a target time period; the target user identifier comprises a target live broadcast user identifier; querying a target identification log matched with the query information from the received identification log, determining live broadcast exception information of a target live broadcast room; and returning the determined live broadcast exception information to the query terminal. The troubleshooting efficiency of the live broadcast exception information can be improved.

Description

Technical Field

[0001] This application relates to the field of multimedia technology, specifically to a data processing method, apparatus, computer equipment, storage medium, and program product. Background Technology

[0002] With the widespread use of live streaming, the number of live streaming platforms is also increasing. On these platforms, streamers start their broadcasts and perform various actions in the live stream room, such as dancing or singing. The live streaming application's secondary pages or the streamer's cover image on the homepage then display various tags to increase user click-through rates and help users filter content they are interested in. If the tag display is abnormal, such as not matching the actual actions performed by the streamer, or the tag not being displayed at all, it is necessary to locate the source of the abnormal tag display information.

[0003] Currently, the typical process involves a streamer discovering an anomaly in a tag, contacting the application's operations department to file a complaint, which then relays the issue to the development or testing department for troubleshooting. Testing then requires reproducing the scenario, and development involves checking logs. This process requires contacting multiple parties for troubleshooting, resulting in low efficiency in locating anomaly information. Summary of the Invention

[0004] This application provides a data processing method, apparatus, computer equipment, storage medium, and program product, which can solve the problem of low efficiency in abnormal information location in related technologies. The technical solution is as follows:

[0005] On the one hand, a data processing method is provided, which includes:

[0006] The system receives identification logs generated by the identification terminal based on the live video stream of at least one live user for at least one time period; the identification terminal is also used to generate corresponding identification tags based on the live video stream and send the identification tags to the corresponding live room for display.

[0007] Receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0008] The system retrieves target identification logs that match the queried information from the received identification logs, and determines the abnormal live streaming information of the target live streaming room based on the target identification logs.

[0009] The identified live stream anomaly information will be returned to the query terminal.

[0010] On the other hand, a data processing method is provided, including:

[0011] The system identifies at least one live streamer's live video stream for at least one time period, generating identification tags and identification logs.

[0012] The identification tags will be sent to the corresponding live stream room for display;

[0013] Send the identification log to the log analysis terminal;

[0014] The log analysis terminal is used to perform the following operations:

[0015] Receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0016] The system retrieves target identification logs that match the queried information from the received identification logs, and determines the abnormal live streaming information of the target live streaming room based on the target identification logs.

[0017] The identified live stream anomaly information will be returned to the query terminal.

[0018] On the other hand, a data processing apparatus is provided, the apparatus comprising:

[0019] The first receiving module is used to receive the recognition logs generated by the recognition terminal based on the live video stream of at least one live user in at least one time period; the recognition terminal is also used to generate corresponding recognition tags based on the live video stream and send the recognition tags to the corresponding live room for display.

[0020] The second receiving module is used to receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0021] The query module is used to query the target identification logs that match the query information from the received identification logs, and determine the live broadcast anomaly information of the target live broadcast room based on the target identification logs;

[0022] The return module is used to return the identified live broadcast anomaly information to the query terminal.

[0023] In one possible implementation, the target user identifier also includes the target audience identifier; when the query module determines the live streaming anomaly information of the target live streaming room based on the target identification log, it is specifically used for:

[0024] Receive live application logs sent by user terminals;

[0025] Query the target application logs that match the query information from the received live application logs;

[0026] Anomalies in the live stream were identified based on the target identification logs and the target application logs.

[0027] In one possible implementation, when the identification terminal generates identification logs based on the live video stream of at least one live user for at least one time period, it specifically uses the following methods:

[0028] Perform at least two sub-processing steps on the live video stream to obtain identification tags;

[0029] For any sub-processing step, generate a sub-log for that sub-step;

[0030] Set the sub-logs of at least two sub-steps as identification logs.

[0031] On the other hand, a data processing apparatus is provided, the apparatus comprising:

[0032] The identification module is used to identify at least one live streamer's live video stream for at least one time period, generating identification tags and identification logs.

[0033] The first sending module is used to send the identification tags to the corresponding live broadcast room for display;

[0034] The second sending module is used to send the identification log to the log analysis terminal;

[0035] The log analysis terminal is used to perform the following operations:

[0036] Receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0037] The system retrieves target identification logs that match the queried information from the received identification logs, and determines the abnormal live streaming information of the target live streaming room based on the target identification logs.

[0038] The identified live stream anomaly information will be returned to the query terminal.

[0039] In one possible implementation, when the identification module identifies and generates identification tags and identification logs for at least one live stream user within at least one time period, it specifically performs the following functions:

[0040] Perform at least two sub-processing steps on the live video stream to obtain identification tags;

[0041] For any sub-processing step, generate a sub-log for that sub-step;

[0042] Set the sub-logs of at least two sub-steps as identification logs.

[0043] In one possible implementation, when the recognition module performs at least two sub-processing steps on the live video stream to obtain the recognition tag, it specifically uses:

[0044] If each sub-processing step yields a corresponding processing result, then proceed to the next sub-processing step in sequence;

[0045] If any sub-processing step fails to obtain the corresponding processing result, a failure message for that sub-processing step is generated and sent to the log analysis terminal, and the next sub-processing step is not performed.

[0046] In one possible implementation, the recognition module performs at least two sub-processing steps on the live video stream to obtain recognition tags; for any sub-processing step, it generates a processing log for that sub-step; when the processing logs of at least two sub-steps are determined as recognition logs, they are specifically used for:

[0047] Perform audio-video separation on the live video stream to obtain live audio and live video, and generate audio-video separation logs;

[0048] Perform video frame segmentation on the live video feed and generate video frame segmentation logs;

[0049] Extract audio information from the live stream audio and generate an information extraction log;

[0050] Based on the live video frame and audio information after video segmentation, identification tags are obtained and tag identification logs are generated.

[0051] Audio and video separation logs, video frame segmentation logs, information extraction logs, and tag recognition logs are identified as recognition logs.

[0052] On the other hand, a computer device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-described data processing method.

[0053] On the other hand, a computer-readable storage medium is provided on which a computer program is stored, which, when executed by a processor, implements the above-described data processing method.

[0054] On the other hand, a computer program product is provided, including a computer program that, when executed by a processor, implements the aforementioned data processing method.

[0055] The beneficial effects of the technical solution provided in this application are:

[0056] The log analysis terminal receives identification logs generated by the identification module for different live video streams from different users at different time periods. When a query is received, the terminal can directly query the target identification log from the received identification logs based on the target live user identifier and the target time period, and locate the live anomaly information to solve the live anomaly problem. This effectively avoids the need for multiple parties to investigate separately and improves the efficiency of locating live anomaly information.

[0057] Furthermore, for each sub-step, a sub-log is generated. When troubleshooting live stream anomalies, each sub-step can be located more quickly, thereby improving the efficiency of locating live stream anomaly information. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0059] Figure 1 A schematic diagram illustrating the implementation environment of a data processing method provided in this application embodiment;

[0060] Figure 2 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0061] Figure 3 A schematic diagram of the query terminal interface provided as an example in this application;

[0062] Figure 4 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0063] Figure 5 A schematic diagram illustrating the data processing scheme provided as an example in this application;

[0064] Figure 6 A schematic diagram of the structure of the identification terminal provided as an example in this application;

[0065] Figure 7 A schematic diagram of the feature extraction module of the facial expression recognition model provided in this application example;

[0066] Figure 8 A comparison chart showing the time taken to investigate anomalies in this application and related technologies;

[0067] Figure 9 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0068] Figure 10 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0069] Figure 11 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0070] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0071] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” indicates implementation as “A,” or implementation as “A,” or implementation as “A and B.”

[0072] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0073] Online live stream users reported that their UID (User Identification) in their live stream room was XXX singing or dancing, but the singing tag was not displayed in the live stream application, resulting in low click-through rates and users missing out on their own hot dances or beautiful songs. After receiving first-hand feedback, the operations staff, or after experiencing the application themselves, discovered a problem with the display of a live stream user tag. They then asked the development team to investigate, and the development team asked the test team to reproduce the issue. The test team then asked the development team to check the logs. Investigating a problem involves many people and a long process.

[0074] Figure 1 This is a schematic diagram of the implementation environment of a data processing method provided in an embodiment of the present invention. See also... Figure 1 The implementation environment includes: a live streaming server 100, live streaming user terminals 101a and 101b, an identification terminal 102, a log analysis terminal 103, and a query terminal 104.

[0075] Specifically, live streaming user terminals 101a and 101b send the live video stream of the current time period to the live streaming server 100, and identification terminal 102 obtains the live video stream from the live streaming server 100. Identification terminal 102 identifies the live video stream, generates identification tags for different live streaming users, and generates identification logs. Identification terminal 102 sends the different identification tags to live streaming user terminals 101a and 101b respectively for display in the live streaming user's live room, and sends the identification logs to log analysis terminal 103. If the live streaming user corresponding to live streaming user terminal 101a finds a problem with the identification tag, live streaming user terminal 101a sends query information to query terminal 104. Query terminal 104 sends the query information to log analysis terminal 103. Log analysis terminal 103 queries the received identification logs for the target identification log that matches the query information, and determines the live streaming anomaly information of the target live streaming user's live room based on the target identification log. Log analysis terminal 103 returns the determined live streaming anomaly information to query terminal 104, and query terminal 104 processes the live streaming anomaly information.

[0076] Understandable, Figure 1 This represents an example application scenario and does not limit the application scenarios of the data processing method in this application.

[0077] Those skilled in the art will understand that a server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server or server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. A terminal can be a smartphone (such as an Android phone, iOS phone, etc.), tablet computer, laptop computer, digital radio receiver, MID (Mobile Internet Device), PDA (Personal Digital Assistant), desktop computer, smart home appliance, in-vehicle terminal (such as in-vehicle navigation terminal, in-vehicle computer, etc.), smart speaker, smartwatch, etc. Terminals and servers can be connected directly or indirectly through wired or wireless communication, but are not limited to these methods. Specific details can be determined based on the actual application scenario requirements and are not limited here.

[0078] Figure 2 This is a flowchart illustrating a data processing method provided in an embodiment of this application. The execution entity of this method can be a log analysis terminal. Figure 2 As shown, the method may include the following steps:

[0079] Step S201: Receive the identification logs sent by the identification terminal, which are generated based on the live video streams of at least one live user in at least one time period.

[0080] Among them, the live streaming users in this application can be the streamers who are currently live streaming.

[0081] Specifically, the identification terminal is also used to generate corresponding identification tags based on the live video stream and send the identification tags to the corresponding live room for display.

[0082] Among them, the identification tags can be tags for the current live streaming content of the live streaming user. For example, what the streamer is doing can be identified by using an identification model to identify the images and audio in the live video stream to obtain identification tags.

[0083] Among them, the identification logs are associated with the live stream user's live stream user identifier, that is, each identification log has a corresponding time period and a corresponding live stream user identifier.

[0084] Specifically, the recognition terminal can perform multiple sub-processing steps on the live video stream, such as audio-video separation, audio frame segmentation, and then recognition. The specific processing procedure for the live video stream will be described in detail below.

[0085] Step S202: Receive query information sent by the query terminal.

[0086] The query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room.

[0087] Specifically, live streaming users can send the live video stream to the live streaming server through their live streaming user terminals, and the recognition terminal can retrieve the live video stream from the live streaming server.

[0088] Specifically, during the live stream, users or viewers may find that the target identification tag displayed in a certain target live stream is abnormal. In this case, the user terminal, i.e., the live stream user terminal or viewer terminal, can send query information to the query terminal, which then sends the query information to the log analysis terminal.

[0089] For example, if a live stream user or viewer finds that the target identification label displayed in the target live stream is incorrect, the live stream user or viewer can send a query message to the query terminal, which can be a terminal used by the operations staff.

[0090] Step S203: Query the target identification log that matches the query information from the received identification log, and determine the live broadcast anomaly information of the target live broadcast room based on the target identification log.

[0091] Among them, abnormal live streaming information can be the reasons for abnormal identification labels. For example, abnormal live streaming information may include the identification module being unable to allocate memory during the processing of the live video stream, or the identification model producing inaccurate identification results when identifying the live video stream, etc.

[0092] Step S204: Return the identified live broadcast anomaly information to the query terminal.

[0093] Specifically, the query terminal can be operated by personnel. After receiving abnormal live broadcast information, the query terminal can process the abnormal live broadcast information; the query terminal can also send the abnormal live broadcast information to the corresponding terminal that processes abnormal information.

[0094] In the above embodiments, the log analysis terminal receives identification logs generated by the identification module for different live video streams of different live users at different time periods. When a query is received, the terminal can directly query the target identification log from the received identification logs based on the target live user identifier and target time period, and locate the live abnormal information, thereby solving the live abnormal problem. This can effectively avoid contacting multiple parties to investigate separately and effectively improve the efficiency of locating live abnormal information.

[0095] like Figure 3 As shown, on the query terminal interface, by entering the target live stream user identifier (the live stream user UID shown in the figure), the viewer identifier (the viewer UID shown in the figure), and the selected time period, the corresponding target identification log can be queried, and live stream anomaly information can be located.

[0096] In some possible ways, the abnormal information can also be further located through the application logs of the viewer's terminal.

[0097] Specifically, step S203, which involves determining the abnormal live streaming information of the target live streaming room based on the target identification log, may include:

[0098] (1) Receive live application logs sent by user terminals;

[0099] (2) Query the target application logs that match the query information from the received live application logs;

[0100] (3) Determine live broadcast anomaly information based on target identification logs and target application logs.

[0101] Specifically, if a target user finds that the target identification tag displayed in the target live room is abnormal when watching the target live room through the user terminal, the live application log can be uploaded to the log analysis terminal.

[0102] Specifically, if the uploaded live application logs are associated with the target user identifier, the target live user identifier, and the target time period, the log analysis module can combine the live application logs and the identification logs to locate abnormal information in the live stream.

[0103] In some possible implementations, when the identification terminal generates identification logs based on the live video stream of at least one live user over at least one time period, it specifically performs the following:

[0104] Perform at least two sub-processing steps on the live video stream to obtain identification tags;

[0105] For any sub-processing step, generate a sub-log for that sub-step;

[0106] Set the sub-logs of at least two sub-steps as identification logs.

[0107] In some possible implementations, the identification log includes at least two sub-logs; each sub-log is generated by the identification terminal performing at least one sub-processing step sequentially on the live video stream.

[0108] Specifically, for each sub-step, a sub-log is generated. When troubleshooting live stream anomalies, each sub-step can be located more quickly, thereby improving the efficiency of locating live stream anomaly information.

[0109] The above data processing method involves the log analysis terminal receiving identification logs generated by the identification module for different live video streams from different users at different time periods. When a query is received, the terminal can directly query the target identification log from the received identification logs based on the target live user identifier and target time period, and locate the live anomaly information, thereby resolving the live anomaly problem. This effectively avoids the need for multiple parties to investigate separately and significantly improves the efficiency of locating live anomaly information.

[0110] Furthermore, for each sub-step, a sub-log is generated. When troubleshooting live stream anomalies, each sub-step can be located more quickly, thereby improving the efficiency of locating live stream anomaly information.

[0111] The above embodiments are described from the perspective of the log analysis terminal. The following will explain the data processing method of this application from the perspective of the identification terminal.

[0112] In one possible implementation, such as Figure 4 As shown, a data processing method is provided that can be applied to an identification terminal. The method may include:

[0113] Step S401: Identify and generate identification tags and identification logs for the live video stream of at least one live user in at least one time period.

[0114] Among them, the identification tags can be tags for the current live stream content of the live stream user. For example, what the streamer is doing can be identified by using an identification model to identify the images and audio in the live video stream to obtain identification tags.

[0115] Specifically, live streaming users can send the live video stream to the live streaming server through their live streaming user terminals, and the recognition terminal can retrieve the live video stream from the live streaming server.

[0116] Specifically, the recognition terminal can perform multiple sub-processing steps on the live video stream, such as audio-video separation, audio frame segmentation, and then recognition. The specific processing procedure for the live video stream will be described in detail below.

[0117] Step S402: Send the identified tags to the corresponding live streaming room for display.

[0118] Specifically, the identification logs are associated with the live stream user's identifier, meaning that each identification log has a corresponding time period and a corresponding live stream user identifier.

[0119] Step S403: Send the identification log to the log analysis terminal.

[0120] The log analysis terminal is used to perform the following operations:

[0121] Receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0122] The system retrieves target identification logs that match the queried information from the received identification logs, and determines abnormal live streaming information of the target live streaming room based on the target identification logs.

[0123] The identified live stream anomaly information will be returned to the query terminal.

[0124] Specifically, during the live stream, users or viewers may find that the target identification tag displayed in a certain target live stream is abnormal. In this case, the user terminal, i.e., the live stream user terminal or viewer terminal, can send query information to the query terminal, which then sends the query information to the log analysis terminal.

[0125] For example, if a live stream user or viewer finds that the target identification label displayed in the target live stream is incorrect, the live stream user or viewer can send a query message to the query terminal, which can be a terminal used by the operations staff.

[0126] Among them, abnormal live streaming information can be the reasons for abnormal identification labels. For example, abnormal live streaming information may include the identification module being unable to allocate memory during the processing of the live video stream, or the identification model producing inaccurate identification results when identifying the live video stream, etc.

[0127] In the above embodiments, the log analysis receives identification logs generated by the identification module for different live video streams of different live users at different time periods. When a query is received, the target identification log can be directly queried from the received identification logs based on the target live user identifier and target time period, and the live abnormal information can be located, thereby solving the live abnormal problem. This can effectively avoid contacting multiple parties to investigate separately and effectively improve the efficiency of locating live abnormal information.

[0128] In some possible implementations, step S401, which identifies at least one live stream user's live video stream for at least one time period and generates identification tags and identification logs, may include:

[0129] Perform at least two sub-processing steps on the live video stream to obtain identification tags;

[0130] For any sub-processing step, generate a sub-log for that sub-step;

[0131] Set the sub-logs of at least two sub-steps as identification logs.

[0132] The sub-processing steps may include audio and video separation, video frame segmentation, information extraction, tag recognition, etc.

[0133] In the specific implementation process, the live video stream undergoes at least two sub-processing steps to obtain identification tags, which may include:

[0134] If each sub-processing step yields a corresponding processing result, then proceed to the next sub-processing step in sequence;

[0135] If any sub-processing step fails to obtain the corresponding processing result, a failure message for that sub-processing step is generated and sent to the log analysis terminal, and the next sub-processing step is not performed.

[0136] Specifically, if each sub-processing step is successful, the next step is performed; if any sub-processing step fails, a failure message is sent to the log analysis terminal.

[0137] Taking at least two sub-processing steps, namely audio-video separation, video framing, information extraction, and tag recognition, as an example, if audio-video separation is successful, video framing is performed; if audio-video separation fails, audio-video separation failure information is sent to the log analysis terminal; if video framing is successful, information extraction is performed; if video framing fails, video framing failure information is returned to the log analysis terminal; if information extraction is successful, tag recognition is performed; if information extraction fails, information extraction failure information is returned to the log analysis terminal.

[0138] In some possible implementations, the live video stream undergoes at least two sub-processing steps to obtain identification tags; for each sub-processing step, a processing log is generated for that sub-step; the processing logs of at least two sub-steps are identified as identification logs, which may include:

[0139] Perform audio-video separation on the live video stream to obtain live audio and live video, and generate audio-video separation logs;

[0140] Perform video frame segmentation on the live video feed and generate video frame segmentation logs;

[0141] Extract audio information from the live stream audio and generate an information extraction log;

[0142] Based on the live video frame and audio information after video segmentation, identification tags are obtained and tag identification logs are generated.

[0143] Audio and video separation logs, video frame segmentation logs, information extraction logs, and tag recognition logs are identified as recognition logs.

[0144] In other embodiments, the sub-processing steps may also include model recognition, that is, using a trained recognition model to recognize the extracted information; the sub-processing steps may also include result prediction, that is, predicting the recognition label corresponding to the extracted information; the sub-processing steps may also include result reporting, that is, reporting the predicted recognition label to the background service.

[0145] Specifically, such as Figure 5As shown, after the identification tag is reported to the backend service, the backend service receives the reported identification tag (backend reception), processes the received identification tag (backend processing), and then reports the received identification tag to the live user terminal (backend reporting). The live user terminal receives, processes, and displays the identification tag (terminal reception, terminal processing, and terminal display). If any sub-processing step fails, the corresponding abnormal information can usually be located. For example, if the identification terminal preprocessing fails, it may be that the stream address of the live video stream is invalid, and the live user may stop broadcasting; if the identification terminal fails to perform audio-video separation and video framing, it may be that the identification terminal cannot allocate memory; if the identification terminal fails to process information, it may be that the information processing result format is incorrect; if the live user terminal displays abnormally, it may be that the fields displayed by the live user terminal are inconsistent with the fields received.

[0146] Specifically, when the identification terminal performs at least two sub-processing steps on the live video stream, the log analysis terminal, when querying the target identification log based on the query information, can query the target sub-log corresponding to each sub-processing step separately. For each target sub-log corresponding to a sub-processing step that is queried, the time corresponding to that target sub-log is determined. If the time interval between the time corresponding to a target sub-log and the target sub-log corresponding to the previous sub-step is less than or equal to a preset time interval, then the two sub-steps are determined to be steps in the same process. If the time interval between the time corresponding to a target sub-log and the target sub-log corresponding to the previous sub-step is greater than the preset time interval, then the two sub-steps are determined to be steps in the same process, and the current target sub-log can be excluded.

[0147] The functions of the identification terminal will be further explained in detail below, taking into account its specific structure.

[0148] like Figure 6 As shown, the identification terminal may include:

[0149] The service module (PredictServer) is used to detect the local port, receive business backend data, including the live stream address and the live stream user identifier, and send the live stream address and the live stream user identifier to the main processing module (SingObserver) for distribution.

[0150] The main processing module is used to process the live stream user address and live stream user identifier sent from the business backend in a unified manner, distribute them to the single stream processing module (PredictProcess), and then submit the processing result to the business backend;

[0151] The single-stream processing module is used to process single streams from live streaming users, including capturing video segments, extracting audio, and other modules such as audio channel processing;

[0152] The audio module (ExtractAudio) is used to extract audio from the video and save it locally.

[0153] The AudioFeature module is used to convert local audio into waveform information, which is then processed by the audio channels and submitted to the transfer learning module.

[0154] The transfer learning module (Transfer) is used to take waveform information as input, process it into 128-dimensional semantic information, and submit it to the recognition module using a transfer model.

[0155] The final recognition result of the recognition module (predict) will be reported to the business backend. The business backend will push the value of the display field flag to the live broadcast user terminal. If it is 1, it will be displayed; if it is 0, it will not be displayed. Each step of the recognition module will have log output. The log output of each step will be checked and the log rules will be defined. According to the rules of each step, if the previous step is successful, the next step will continue. If the previous step fails, such as the receiving stream fails, then failure will be returned directly to find the cause of the problem.

[0156] The overall process of the entire identification terminal is as follows:

[0157] Receive live video stream; if unsuccessful, return a failure message; if successful, perform audio / video separation; if audio / video separation fails, return a failure message; if successful, perform preprocessing; if preprocessing fails, return a failure message; if preprocessing is successful, perform audio / video recognition; if audio / video recognition fails, return a failure message; if audio / video recognition is successful, report the recognized tags to the business backend; if result reporting fails, return a failure message; if result reporting is successful, the business backend reports the recognized tags to the user terminal; if reporting to the user terminal fails, return a failure message; if reporting to the user terminal is successful, display the recognized tags in the user terminal's live stream room.

[0158] In practice, logs are only displayed on the terminal after all processes in the front end have been completed. If any step in the front end fails, the identification tag cannot be displayed. This avoids developers having to search logs from various modules when querying exceptions, thus improving efficiency.

[0159] The above data processing methods will be explained from the perspective of identifying terminal and log analysis terminal interactions.

[0160] When a live streamer is broadcasting, the business backend pushes the live video stream of the live streamer for the current time period to the recognition terminal.

[0161] The recognition terminal identifies the video content of the live video stream, obtains the corresponding recognition tags, and generates a recognition log for the current time period.

[0162] The identification terminal sends the identification tag to the business backend;

[0163] The back-end system will identify the tags and send them to the live stream for display.

[0164] The identification terminal sends the identification logs to the log analysis terminal;

[0165] If a user terminal (live streaming user terminal or viewer terminal) discovers that the identification tag displayed in the live streaming room is abnormal, it sends a query message to the query terminal.

[0166] The query terminal sends query information to the log analysis terminal;

[0167] The log analysis terminal queries the target identification logs that match the query information from the received identification logs, and determines the live broadcast anomaly information of the target live broadcast room based on the target identification logs;

[0168] The log analysis terminal returns the identified live broadcast anomaly information to the query terminal.

[0169] like Figure 7 As shown in the attached figures, the above data processing process will be further explained in detail below.

[0170] During the live stream, the business backend pushes the live video stream of the live stream user to the recognition terminal;

[0171] The recognition terminal performs preprocessing, audio-video separation, audio framing, information processing, model recognition, result prediction, result output, and result reporting to the business backend for the live video stream; and generates recognition logs that are associated with the live user identifier and the current time period, and sends the recognition logs to the log analysis terminal;

[0172] The business backend will identify the tags and push them to the user's terminal live broadcast room for display;

[0173] The log analysis terminal includes a web server and log parsing scripts;

[0174] If viewers find the identification tags displayed in the live broadcast room to be abnormal, the user terminal will upload application logs that are associated with both the viewer's identification and the current time period to the log analysis terminal.

[0175] The query terminal (i.e., the visualization operation platform shown in the figure) receives the target live user identifier and target time period to be queried from the user terminal (viewer terminal or live user terminal), or may also include the target identifier, and sends the target live user identifier, target viewer identifier and target time period to the network service of the log analysis terminal.

[0176] The network service uses a log parsing script to query the corresponding target identification logs and target application logs, and determines the live broadcast anomaly information based on the target identification logs and target application logs;

[0177] The network service will return the analyzed live stream anomaly information to the query terminal.

[0178] The effects of the data processing method of this application will be illustrated below with reference to the accompanying drawings.

[0179] like Figure 8 As shown, when abnormal information appears in the live broadcast room, the relevant technical staff contact the application's operations department to complain, and the operations department then reports it to the development or testing department for troubleshooting. The testing department also needs to reproduce the scenario, and the development department then checks the logs. This process requires contacting multiple parties for troubleshooting, which can take up to 5-10 hours. However, using the data processing method in this application, it only takes 5-10 minutes to locate the abnormal information in the live broadcast.

[0180] The above data processing method involves the log analysis terminal receiving identification logs generated by the identification module for different live video streams from different users at different time periods. When a query is received, the terminal can directly query the target identification log from the received identification logs based on the target live user identifier and target time period, and locate the live anomaly information, thereby resolving the live anomaly problem. This effectively avoids the need for multiple parties to investigate separately and significantly improves the efficiency of locating live anomaly information.

[0181] Furthermore, for each sub-step, a sub-log is generated. When troubleshooting live stream anomalies, each sub-step can be located more quickly, thereby improving the efficiency of locating live stream anomaly information.

[0182] Figure 9 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application. Figure 9 As shown, the device includes:

[0183] The first receiving module 901 is used to receive the identification logs generated by the identification terminal based on the live video stream of at least one live user in at least one time period; the identification terminal is also used to generate corresponding identification tags based on the live video stream and send the identification tags to the corresponding live room for display.

[0184] The second receiving module 902 is used to receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0185] The query module 903 is used to query the target identification log that matches the query information from the received identification log, and determine the live broadcast anomaly information of the target live broadcast room based on the target identification log;

[0186] Return module 904 is used to return the identified live broadcast anomaly information to the query terminal.

[0187] In one possible implementation, the target user identifier also includes the target audience identifier; when determining the live broadcast anomaly information of the target live broadcast room based on the target identification log, the query module 903 is specifically used for:

[0188] Receive live application logs sent by user terminals;

[0189] Query the target application logs that match the query information from the received live application logs;

[0190] Anomalies in the live stream were determined based on the target identification logs and the target application logs.

[0191] In one possible implementation, when the identification terminal generates identification logs based on the live video stream of at least one live user for at least one time period, it specifically uses the following methods:

[0192] Perform at least two sub-processing steps on the live video stream to obtain identification tags;

[0193] For any sub-processing step, generate a sub-log for that sub-step;

[0194] Set the sub-logs of at least two sub-steps as identification logs.

[0195] Figure 10 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application. Figure 10 As shown, the device includes:

[0196] The identification module 1001 is used to identify the live video stream of at least one live user in at least one time period, generate identification tags and identification logs;

[0197] The first sending module 1002 is used to send the identification tag to the corresponding live broadcast room for display.

[0198] The second sending module 1003 is used to send the identification log to the log analysis terminal;

[0199] The log analysis terminal is used to perform the following operations:

[0200] Receive query information sent by the query terminal; the query information includes the target user identifier and the target time period; the target user identifier includes the target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room;

[0201] The system retrieves target identification logs that match the queried information from the received identification logs, and determines the abnormal live streaming information of the target live streaming room based on the target identification logs.

[0202] The identified live stream anomaly information will be returned to the query terminal.

[0203] In one possible implementation, when the identification module 1001 identifies and generates identification tags and identification logs for at least one live stream user's live video stream over at least one time period, it is specifically used for:

[0204] Perform at least two sub-processing steps on the live video stream to obtain identification tags;

[0205] For any sub-processing step, generate a sub-log for that sub-step;

[0206] Set the sub-logs of at least two sub-steps as identification logs.

[0207] In one possible implementation, when the identification module 1001 performs at least two sub-processing steps on the live video stream to obtain the identification tag, it is specifically used for:

[0208] If each sub-processing step yields a corresponding processing result, then proceed to the next sub-processing step in sequence;

[0209] If any sub-processing step fails to obtain the corresponding processing result, a failure message for that sub-processing step is generated and sent to the log analysis terminal, and the next sub-processing step is not performed.

[0210] In one possible implementation, the recognition module 1001 performs at least two sub-processing steps on the live video stream to obtain recognition tags; for any sub-processing step, it generates a processing log for that sub-step; and when determining the processing logs of at least two sub-steps as recognition logs, it is specifically used for:

[0211] Perform audio-video separation on the live video stream to obtain live audio and live video, and generate audio-video separation logs;

[0212] Perform video frame segmentation on the live video feed and generate video frame segmentation logs;

[0213] Extract audio information from the live stream audio and generate an information extraction log;

[0214] Based on the live video frame and audio information after video segmentation, identification tags are obtained and tag identification logs are generated.

[0215] Audio and video separation logs, video frame segmentation logs, information extraction logs, and tag recognition logs are identified as recognition logs.

[0216] The aforementioned data processing device, the log analysis terminal, receives identification logs generated by the identification module for different live video streams of different live users at different time periods. When a query is received, it can directly query the target identification log from the received identification log based on the target live user identifier and target time period, and locate the live abnormal information, thereby solving the live abnormal problem. This can effectively avoid contacting multiple parties to investigate separately and effectively improve the efficiency of locating live abnormal information.

[0217] Furthermore, for each sub-step, a sub-log is generated. When troubleshooting live stream anomalies, each sub-step can be located more quickly, thereby improving the efficiency of locating live stream anomaly information.

[0218] The data processing device in this embodiment can execute the data processing method shown in the above embodiments of this application. The implementation principle is similar and will not be described again here.

[0219] Figure 11 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. For example... Figure 11 As shown, the computer device includes: a memory and a processor; at least one program, stored in the memory, which, when executed by the processor, can achieve the following compared to the prior art:

[0220] The log analysis terminal receives identification logs generated by the identification module for different live stream users at different time periods. Upon receiving a query, it can directly retrieve the target identification log from the received logs based on the target live stream user's identifier and the target time period, thus locating live stream anomalies and resolving issues. This effectively avoids the need for multiple parties to investigate separately, significantly improving the efficiency of anomaly location. Each sub-step generates a sub-log, allowing for faster identification of each sub-step during anomaly investigation, further enhancing the efficiency of anomaly location.

[0221] In one alternative embodiment, a computer device is provided, such as Figure 11 As shown, Figure 11The computer device 1100 shown includes a processor 1101 and a memory 1103. The processor 1101 and the memory 1103 are connected, for example, via a bus 1102. Optionally, the computer device 1100 may further include a transceiver 1104, which can be used for data interaction between the computer device and other computer devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 1104 is not limited to one type, and the structure of the computer device 1100 does not constitute a limitation on the embodiments of this application.

[0222] Processor 1101 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 1101 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0223] Bus 1102 may include a pathway for transmitting information between the aforementioned components. Bus 1102 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 1102 may be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0224] The memory 1103 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0225] The memory 1103 is used to store application code (computer program) for executing the solution of this application, and its execution is controlled by the processor 1101. The processor 1101 is used to execute the application code stored in the memory 1103 to implement the content shown in the foregoing method embodiments.

[0226] Computer equipment includes, but is not limited to: virtualized computer equipment, virtual machines, servers, service clusters, and user terminals.

[0227] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content of the data processing method described in the foregoing method embodiments.

[0228] This application provides a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the data processing method described above.

[0229] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0230] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, 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 device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0231] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0232] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0233] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0234] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0235] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The name of a module does not necessarily limit the module itself; for example, an identification terminal can also be described as a "module for identifying live video streams".

[0236] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A data processing method, characterized in that, The method, applied to a log analysis terminal, includes: The system receives identification logs generated by the identification terminal based on the live video stream of at least one live user within at least one time period; the identification terminal is further configured to generate corresponding identification tags based on the live video stream and send the identification tags to the corresponding live room for display; wherein, the identification logs include sub-logs generated by the identification terminal for each sub-step of the live video stream in sequence; The system receives query information sent by a query terminal; the query information includes a target user identifier and a target time period; the target user identifier includes a target live stream user identifier; the query information is sent based on an anomaly in the target identification tag displayed in the target live stream. The system queries the received identification logs to find target identification logs that match the query information. The target identification logs include sub-logs that match the target live stream user identifier and target time period. Based on the target identification logs, the system determines the live stream anomaly information of the target live stream room. The identified live stream anomaly information is returned to the query terminal; The identification log is generated by the identification terminal in the following way: The live video stream is subjected to audio-video separation to obtain live audio and live video, and an audio-video separation log is generated. The live video frame is segmented to generate a video frame log; Extract the audio information from the live stream audio and generate an information extraction log; Based on the live video frame after video segmentation and the audio information, the identification tags are obtained and a tag identification log is generated; The audio / video separation log, the video frame segmentation log, the information extraction log, and the tag recognition log are identified as the recognition log.

2. The data processing method according to claim 1, characterized in that, The target user identifier also includes a target viewer identifier; determining the live streaming anomaly information of the target live streaming room based on the target identification log includes: Receive live application logs sent by user terminals; Query the target application logs that match the query information from the received live application logs; The live stream anomaly information is determined based on the target identification log and the target application log.

3. The data processing method according to claim 1, characterized in that, When the identification terminal generates identification logs based on the live video stream of at least one live user for at least one time period, it is specifically used for: The live video stream is subjected to at least two sub-processing steps to obtain the identification tag; For any sub-processing step, generate a sub-log for that sub-step; Set the sub-logs of the at least two sub-steps as the identification logs.

4. A data processing method, characterized in that, Applied to an identification terminal, the method includes: The system identifies and generates identification tags and identification logs for the live video stream of at least one live user within at least one time period; wherein the identification logs include sub-logs generated by the identification terminal for each sub-step of the live video stream in sequence. The identification tag is sent to the corresponding live stream room for display; The identification log is sent to the log analysis terminal; The log analysis terminal is used to perform the following operations: The system receives query information sent by a query terminal; the query information includes a target user identifier and a target time period; the target user identifier includes a target live stream user identifier; the query information is sent based on an anomaly in the target identification tag displayed in the target live stream. The system queries the received identification logs to find target identification logs that match the query information. The target identification logs include sub-logs that match the target live stream user identifier and target time period. Based on the target identification logs, the system determines the live stream anomaly information of the target live stream room. The identified live stream anomaly information is returned to the query terminal; The identification log is generated by the identification terminal in the following way: The live video stream is separated into audio and video to obtain live audio and live video, and an audio-video separation log is generated. The live video frame is segmented to generate a video frame log; Extract the audio information from the live stream audio and generate an information extraction log; Based on the live video frame after video segmentation and the audio information, the identification tags are obtained and a tag identification log is generated; The audio / video separation log, the video frame segmentation log, the information extraction log, and the tag recognition log are identified as the recognition log.

5. The data processing method according to claim 4, characterized in that, The process of identifying and generating identification tags and identification logs for at least one live stream user's live video stream over at least one time period includes: The live video stream is subjected to at least two sub-processing steps to obtain the identification tag; For any sub-processing step, generate a sub-log for that sub-step; Set the sub-logs of the at least two sub-steps as the identification logs.

6. The data processing method according to claim 5, characterized in that, The step of performing at least two sub-processing steps on the live video stream to obtain the identification tag includes: If each sub-processing step yields a corresponding processing result, then proceed to the next sub-processing step in sequence; If any sub-processing step fails to obtain the corresponding processing result, a failure message for that sub-processing step is generated and sent to the log analysis terminal, and the next sub-processing step is not performed.

7. A data processing apparatus, characterized in that, The device, used in a log analysis terminal, includes: The first receiving module is used to receive recognition logs generated by the recognition terminal based on the live video stream of at least one anchor in at least one time period; the recognition terminal is also used to generate corresponding recognition tags based on the live video stream and send the recognition tags to the corresponding live room for display; wherein, the recognition logs include sub-logs generated by the recognition terminal for each sub-step of the live video stream in sequence; The second receiving module is used to receive query information sent by the query terminal; the query information includes a target user identifier and a target time period; the target user identifier includes a target live stream user identifier; the query information is sent based on the abnormality of the target identification tag displayed in the target live stream room; The query module is used to query the target identification logs that match the query information from the received identification logs. The target identification logs include sub-logs that are matched according to the target live stream user identifier and the target time period. Based on the target identification logs, the live stream anomaly information of the target live stream room is determined. The return module is used to return the identified live broadcast anomaly information to the query terminal; The identification log is generated by the identification terminal in the following way: The live video stream is separated into audio and video to obtain live audio and live video, and an audio-video separation log is generated. The live video frame is segmented to generate a video frame log; Extract the audio information from the live stream audio and generate an information extraction log; Based on the live video frame after video segmentation and the audio information, the identification tags are obtained and a tag identification log is generated; The audio / video separation log, the video frame segmentation log, the information extraction log, and the tag recognition log are identified as the recognition log.

8. A data processing apparatus, characterized in that, The device, used in an identification terminal, includes: The identification module is used to identify at least one live streaming user's live video stream for at least one time period, generate identification tags and identification logs; wherein, the identification logs include sub-logs generated by the identification terminal for each sub-step of the live video stream in sequence; The first sending module is used to send the identification tag to the corresponding live broadcast room for display; The second sending module is used to send the identification log to the log analysis terminal; The log analysis terminal is used to perform the following operations: The system receives query information sent by a query terminal; the query information includes a target user identifier and a target time period; the target user identifier includes a target live stream user identifier; the query information is sent based on an anomaly in the target identification tag displayed in the target live stream. The system queries the received identification logs to find target identification logs that match the query information. The target identification logs include sub-logs that match the target live stream user identifier and target time period. Based on the target identification logs, the system determines the live stream anomaly information of the target live stream room. The identified live stream anomaly information is returned to the query terminal; The identification log is generated by the identification terminal in the following way: The live video stream is separated into audio and video to obtain live audio and live video, and an audio-video separation log is generated. The live video frame is segmented to generate a video frame log; Extract the audio information from the live stream audio and generate an information extraction log; Based on the live video frame after video segmentation and the audio information, the identification tags are obtained and a tag identification log is generated; The audio / video separation log, the video frame segmentation log, the information extraction log, and the tag recognition log are identified as the recognition log.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the data processing method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the data processing method according to any one of claims 1 to 6.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the data processing method according to any one of claims 1 to 6.

Images