A method and device for intelligent marking and display of video content based on ai pre-detection

Abstract

The invention relates to the technical field of combination of front-end video processing and artificial intelligence application, in particular to a video content intelligent mark display method and device based on AI pre-detection, and the method comprises the steps: building a mapping relation between detection problems and a video time axis, and carrying out the intelligent grouping of adjacent detection problems through a time merging threshold value, the playing time can be monitored in real time in the video playing process, the visual mark and information display of the detection problem group accurately matched with the current playing time period can be dynamically controlled, interference caused by frequent mark switching is avoided, key problems are ensured to be presented in time, and the user experience is improved. Therefore, the perception efficiency and interaction experience of the user on the video content problem are improved.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202511637007.9 (22) Application Date 2025.11.10 (71) Applicant Beijing Qingsong Yikang Information Technology Co., Ltd. Address Room 716, 7th Floor, Building 2, No. 28, Andingmen East Street, Dongcheng District, Beijing 100007 (72) Inventors Yang Yin, Guan Wenfeng, Liu Junpei, Huang Xiandong, Zhang Da (74) Patent Agency Beijing Huaxia Taihe Intellectual Property Agency Co., Ltd. 11662 Patent Attorney Li Man (51) Int.Cl. H04N 21 / 234 (2011.01) H04N 21 / 235 (2011.01) H04N 21 / 44 (2011.01) H04N 21 / 462 (2011.01) H04N 21 / 845(2011.01) H04N 21 / 8547(2011.01) G06N 5 / 045(2023.01) (54) Invention Title: A Method and Apparatus for Intelligent Tagging and Displaying Video Content Based on AI Pre-detection (57) Abstract: This application relates to the technical field of front-end video processing combined with artificial intelligence applications, specifically to a method and apparatus for intelligent tagging and displaying video content based on AI pre-detection. This application establishes a mapping relationship between detection issues and video timelines, and uses time merging thresholds to intelligently group adjacent detection issues. It can monitor the playback time in real time during video playback, dynamically control the visualization tagging and information display of the detection issue group that is precisely matched with the current playback period, avoids the interference caused by frequent tag switching, and ensures that key issues are presented in a timely manner, thereby improving the user's perception efficiency and interactive experience of video content issues. Claims 2 pages, Description 14 pages, Drawings 2 pages, CN 121547612 A 2026.02.17 CN 1 21 54 76 12 A 1. A method for intelligent labeling and displaying video content based on AI pre-detection, characterized in that it includes: acquiring AI pre-detection data of the current video and establishing a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data includes at least one detection question associated with a video timestamp; merging multiple detection questions with adjacent timestamps into a detection question group based on a preset time merging threshold; during the playback of the current video, monitoring the current playback time in real time, and dynamically controlling the display state of the visual labels and information of the detection question group corresponding to the current playback time based on the time difference between the current playback time and the reference timestamp of the detection question group, wherein the reference timestamp of the detection question group is the start time of the first detection question in the detection question group.2. The AI-based pre-detection-based intelligent labeling and display method for video content, as described in claim 1, is characterized in that, based on a preset time merging threshold, multiple detection issues with adjacent timestamps are merged into a detection issue group, including: sorting all detection issues in ascending order according to their timestamps to obtain a detection issue list; traversing the sorted detection issue list, if the difference between the current detection issue and the baseline timestamp of the current detection issue group is less than the time merging threshold, then merging it into the current detection issue group; otherwise, creating a new detection issue group starting from the current detection issue. 3. The AI-based pre-detection-based intelligent labeling and display method for video content, as described in claim 1, is characterized in that, establishing a mapping relationship between the detection issues and the playback timeline of the current video, includes: classifying the detection items in the AI ​​pre-detection data into global detection issues and time-point detection issues; assigning a unique identifier to each detection issue; based on the total duration of the current video, converting the timestamp of each detection issue into a relative position percentage on the video progress bar, and establishing the mapping relationship. 4. The AI-based pre-detection-based intelligent labeling and display method for video content, as described in claim 3, is characterized in that, based on the total duration of the current video, the timestamp of each detection issue is converted into a relative position percentage on the video progress bar, comprising: obtaining the total duration of the current video; and for each detection issue, obtaining the relative position percentage of each detection issue on the video progress bar using a preset percentage formula, wherein the relative position percentage is used to determine the rendering position of the visual label of the detection issue on the progress bar. 5. The intelligent labeling and display method for video content based on AI pre-detection according to claim 1, characterized in that, based on the time difference between the current playback time and the reference timestamp of the detection problem group, the display state of the visual label and information of the detection problem group corresponding to the current playback time is dynamically controlled, including: obtaining the reference timestamp of the detection problem group and the current playback time; determining the time difference between the reference timestamp of the detection problem group and the current playback time using a preset time difference formula; when the time difference is less than or equal to a preset display time window, controlling the visual label of the detection problem group to be highlighted and displaying the detailed information of the detection problem group in the user interface; when the time difference is greater than the display time window, controlling the visual label of the detection problem group to return to the normal display state and hiding the detailed information of the detection problem group in the user interface. 6. The intelligent labeling and display method for video content based on AI pre-detection according to claim 1, characterized in that, the method further includes: in response to user operation, deleting or restoring a specific detection problem from the detection problem group, the specific steps of which are:Obtain a preset deletion list, wherein the deletion list contains unique identifiers of deleted detection issues; In response to a user's deletion operation on a first detection issue, add the unique identifier of the first detection issue to the deletion list, and mark the first detection issue as deleted in the user interface; In response to a user's restoration operation on a deleted second detection issue, remove the unique identifier of the second detection issue from the deletion list, and mark the second detection issue as normally displayed in the user interface. 7. The video content intelligent labeling and display method based on AI pre-detection according to claim 6, wherein the method further includes: automatically generating rejection reason text for video review based on all undeleted detection issues according to a preset structured template, specifically the following steps: Obtain all global detection issues and time-point detection issues; Filter out the detection issues in the deletion list from all issues; Sort the remaining detection issues after filtering in ascending order according to their timestamps; Format the sorted detection issues into text according to a preset template, wherein for time-point detection issues, their timestamps are converted to MM:SS format and then concatenated with the issue description; Summarize all formatted text to generate a complete rejection reason. 8. A video content intelligent labeling and display device based on AI pre-detection, characterized in that it comprises: a data acquisition and mapping module, used to acquire AI pre-detection data of the current video and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data includes at least one detection question associated with a video timestamp; a question merging module, used to merge multiple detection questions with adjacent timestamps into a detection question group based on a preset time merging threshold; and an interactive control module, used to monitor the current playback time in real time during the playback of the current video, and dynamically control the display status of the visual labels and information of the detection question group corresponding to the current playback time based on the time difference between the current playback time and the reference timestamp of the detection question group, wherein the reference timestamp of the detection question group is the start time of the first detection question in the detection question group. 9. An electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus, characterized in that: the memory is used to store a computer program; the processor is used to execute the AI-based pre-detection video content intelligent tagging display method according to any one of claims 1 to 7 by running the computer program stored in the memory. 10. A computer-readable storage medium, characterized in that the storage medium stores a computer program, wherein the computer program is configured to execute the AI-based pre-detection video content intelligent tagging display method according to any one of claims 1 to 7 when running.Intelligent labeling and display method for video content. Claims 2 / 2 Page 3 CN 121547612 A Intelligent labeling and display method and device for video content based on AI pre-detection Technical Field

[0001] This application relates to the technical field of front-end video processing combined with artificial intelligence applications, specifically to an intelligent labeling and display method and device for video content based on AI pre-detection. Background Art

[0002] With the explosive growth of online video content, video content review has become a crucial part of online platform operation. Traditional pure manual review methods are inefficient and difficult to cope with massive amounts of content. To this end, the industry has generally introduced artificial intelligence (AI) technology to pre-detect videos and automatically identify illegal or problematic content segments in order to improve review efficiency.

[0003] However, existing video review systems that combine AI detection still have significant technical defects at the front-end application level, which seriously affect the actual operating experience and final efficiency of reviewers. First, the AI ​​detection results are usually presented independently in the form of back-end data reports, which are separate from the front-end video playback interface. Reviewers need to frequently switch their gaze and operation focus between the report and the player, resulting in an incoherent workflow. Secondly, and more importantly, the existing system lacks a high-precision time synchronization and visualization mechanism, making it impossible to accurately locate the problem points detected by AI on the video playback timeline and display them in real time with intuitive visual markers. This makes it difficult for reviewers to quickly understand and locate the specific moment when the problem occurred. In addition, when multiple detection problems occur in a short period of time, the markers on the interface will overlap due to crowding and cannot be effectively distinguished. At the same time, the system also lacks the ability to dynamically manage detection points and provide intelligent decision support based on detection results.

[0004] Therefore, there is an urgent need in the field for a front-end technology solution that can accurately synchronize AI detection results with the video playback timeline, intelligently manage detection points, and provide a smooth interactive experience, so as to fundamentally improve the accuracy and efficiency of video content review. Summary of the Invention

[0005] The purpose of this application is to provide a video content intelligent marker display method and device based on AI pre-detection, so as to solve the problem in the prior art that it is impossible to accurately locate the problems detected by AI on the video playback timeline and display them in real time with intuitive visual markers.

[0006] To achieve the above objectives, the technical solution adopted in this application is as follows: According to one aspect of the embodiments of this application, a method for intelligent labeling and displaying video content based on AI pre-detection is provided, comprising: acquiring AI pre-detection data of the current video, and establishing a mapping relationship between detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data includes at least one detection question associated with a video timestamp; merging multiple detection questions with adjacent timestamps into a detection question group based on a preset time merging threshold; and in the current video...During the playback of the previous video, the current playback time is monitored in real time. Based on the time difference between the current playback time and the reference timestamp of the detection problem group, the display status of the visual markers and information of the detection problem group corresponding to the current playback time is dynamically controlled. The reference timestamp of the detection problem group is the start time of the first detection problem in the detection problem group.

[0007] According to the above technical means, by establishing a mapping relationship between the detection problem and the video timeline, and using the time merging threshold to intelligently group adjacent detection problems, the playback time can be monitored in real time during video playback, and the display of the visual markers and information of the detection problem group that accurately matches the current playback period can be dynamically controlled. This avoids the interference caused by frequent switching of markers and ensures that key problems are presented in a timely manner, thereby improving the user's perception efficiency and interactive experience of video content problems.

[0008] Further, based on a preset time merging threshold, multiple detection issues with adjacent timestamps are merged into a detection issue group, including: sorting all detection issues in ascending order according to their timestamps to obtain a detection issue list; traversing the sorted detection issue list, if the difference between the current detection issue and the baseline timestamp of the current detection issue group is less than the time merging threshold, then merging it into the current detection issue group; otherwise, creating a new detection issue group starting from the current detection issue.

[0009] According to the above technical means, by sorting detection issues in ascending order according to timestamps and merging detection issues with adjacent timestamps into groups based on a preset time merging threshold, it is possible to effectively integrate detection issues with similar times, avoid scattered processing, and improve the efficiency of issue management and the continuity of analysis.

[0010] Further, establishing a mapping relationship between detection issues and the playback timeline of the current video includes: classifying the detection items in the AI ​​pre-detection data into global detection issues and time point detection issues; assigning a unique identifier to each detection issue; and based on the total duration of the current video, converting the timestamp of each detection issue into a relative position percentage on the video progress bar to establish a mapping relationship.

[0011] According to the above technical means, by classifying the detection problems and assigning unique identifiers, and combining the total video duration to convert the timestamps into a relative position percentage on the progress bar, a precise and standardized mapping between the detection problems and the video timeline is achieved. This not only clearly distinguishes between global problems and problems in specific time periods, but also ensures the consistency of problem location across videos of different durations, providing a reliable data foundation for subsequent dynamic display and interactive control.

[0012] Further, based on the total duration of the current video, the timestamp of each detection problem is converted into a relative position percentage on the video progress bar, including: obtaining the total duration of the current video; for each detection problem, obtaining the relative position percentage of each detection problem on the video progress bar using a preset percentage formula, wherein the relative position percentage is used for...Determine the rendering position of the visual marker for the detected problem on the progress bar.

[0013] According to the above technical means, by converting the timestamp of the detected problem into a percentage of the relative position on the progress bar based on the total video duration, the standardized positioning of the detected problem on the timeline is realized, ensuring the comparability and consistency of the problem marker positions in videos of different durations. At the same time, it provides data support for the accurate rendering of the visual marker on the progress bar, effectively improving the user's intuitive perception of the distribution of video problems.

[0014] Further, based on the time difference between the current playback time and the reference timestamp of the detected problem group, the display status of the visual marker and information of the detected problem group corresponding to the current playback time is dynamically controlled, including: obtaining the reference timestamp of the detected problem group and the current playback time; determining the time difference between the reference timestamp of the detected problem group and the current playback time using a preset time difference formula; when the time difference is less than or equal to the preset display time window, the visual marker of the detected problem group is highlighted and the detailed information of the detected problem group is displayed in the user interface; when the time difference is greater than the display time window, the visual marker of the detected problem group is restored to the normal display state and the detailed information of the detected problem group is hidden in the user interface.

[0015] According to the above technical means, by calculating the time difference between the current playback time and the baseline timestamp of the detection problem group, and dynamically controlling the display status of the visualization markers and information according to the preset display time window, the detection problem group closely related to the current playback period can be highlighted accurately and timely when the user is watching the video, attracting the user's attention and presenting detailed information in a highlighted form, while restoring normal display and hiding details during irrelevant periods to avoid information interference, thereby significantly improving the user's attention efficiency and interactive experience for video detection problems.

[0016] Further, the method also includes: in response to a user operation, deleting or restoring a specific detection problem from the detection problem group, specifically: obtaining a preset deletion list, wherein the deletion list contains a unique identifier of the deleted detection problem; in response to the user's deletion operation on the first detection problem, adding the unique identifier of the first detection problem to the deletion list, and marking the first detection problem as deleted in the user interface; in response to the user's restoration operation on the deleted second detection problem, removing the unique identifier of the second detection problem from the deletion list, and marking the second detection problem as normally displayed in the user interface.

[0017] According to the above technical means, by setting a deletion list containing the unique identifier of the deleted detection problem, the identifier of the detection problem to be deleted can be quickly added to the list and marked as deleted when the user operates, achieving accurate deletion; at the same time, when the user needs to restore, the corresponding identifier can be removed from the list and the normal display can be restored. This flexible...The deletion and restoration mechanism gives users more autonomous and convenient management capabilities over detection issues, effectively improving the efficiency and experience of user interaction with detection issues.

[0018] Furthermore, the method also includes: based on all undeleted detection issues, automatically generating rejection reason text for video review according to a preset structured template. The specific steps are: obtaining all global detection issues and time-point detection issues; filtering out detection issues from the deletion list from all issues; sorting the remaining detection issues after filtering in ascending order according to their timestamps; formatting the sorted detection issues into text according to a preset template, wherein, for time-point detection issues, their timestamps are converted to MM:SS format and then concatenated with the issue description; summarizing all formatted text to generate a complete rejection reason.

[0019] Based on the above technical means, based on the detection issues that have not been deleted, by filtering the deletion items, sorting by timestamp and formatting the text with a preset template, especially by standardizing the timestamp of the time point detection issues into MM:SS format and splicing the description, a structured video review rejection reason text is finally generated. This can automatically and accurately integrate the issue information, making the rejection reasons clear and the content standardized, which greatly improves the efficiency and accuracy of the reason feedback in the video review process and makes it convenient for reviewers to quickly understand and handle.

[0020] According to another aspect of the embodiments of this application, a video content intelligent labeling and display device based on AI pre-detection is also provided, comprising: a data acquisition and mapping module, used to acquire AI pre-detection data of the current video and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data includes at least one detection question associated with a video timestamp; a question merging module, used to merge multiple detection questions with adjacent timestamps into a detection question group based on a preset time merging threshold; a position determination module, used to convert the reference timestamp of each detection question group into a relative position percentage on the video progress bar based on the total duration of the current video, wherein the reference timestamp of the detection question group is the start time of the first detection question in the detection question group; and an interactive control module, used to monitor the current playback time in real time during the playback of the current video, and dynamically control the display status of the visual labels and information of the detection question group corresponding to the current playback time based on the time difference between the current playback time and the reference timestamp of the detection question group.

[0021] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein the memory is used to store a computer program; and the processor is used to execute the method steps of any of the above embodiments by running the computer program stored in the memory.

[0022] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the storage medium, wherein the computer program is configured to execute the method steps in any of the above embodiments when running.

[0023] Beneficial effects of this application: Specification 3 / 14 pages 6 CN 121547612 A This application establishes a mapping relationship between detection problems and video timelines, and uses time merging thresholds to intelligently group adjacent detection problems. It can monitor the playback time in real time during video playback, dynamically control the visualization marking and information display of detection problem groups that are precisely matched with the current playback period, which avoids the interference caused by frequent switching of markings and ensures that key problems are presented in a timely manner, thereby improving the user's perception efficiency and interactive experience of video content problems. Brief Description of the Drawings

[0024] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 is a schematic diagram of the hardware environment of an optional AI pre-detection-based intelligent tagging display method for video content provided in an embodiment of this application; Figure 2 is a flowchart of an optional AI pre-detection-based intelligent tagging display method for video content provided in an embodiment of this application; Figure 3 is a structural block diagram of an optional AI pre-detection-based intelligent tagging display device for video content provided in an embodiment of this application; Figure 4 is a structural block diagram of an optional electronic device provided in an embodiment of this application. Detailed Description

[0027] In order to enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover...The inclusion is non-exclusive; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices.

[0029] According to one aspect of an embodiment of this application, a method for intelligently labeling and displaying video content based on AI pre-detection is provided. Optionally, in this embodiment, the above-mentioned method for intelligently labeling and displaying video content based on AI pre-detection can be applied to a hardware environment consisting of a terminal and a server. The server is connected to the terminal via a network and can be used to provide services to the terminal or a client installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services to the server.

[0030] The above-mentioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The above-mentioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The above-mentioned wireless network may include, but is not limited to, at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal is not limited to PCs, mobile phones, tablets, etc.

[0031] The AI-based pre-detection video content intelligent tagging display method of this application embodiment can be executed by a server, by a terminal, or by both a server and a terminal. The terminal executing the AI-based pre-detection video content intelligent tagging display method of this application embodiment can also be executed by a client installed on it.

[0032] Taking the execution of the AI-based pre-detection video content intelligent tagging display method of this embodiment by a server as an example, please refer to Figure 1. Figure 1 is a schematic diagram of the hardware environment of an optional AI-based pre-detection video content intelligent tagging display method provided in this application embodiment. As shown in Figure 1, the hardware environment of the AI-based pre-detection video content intelligent tagging display method includes: a terminal 102, and a server 104 connected to the terminal 102 via a network. Server 104 is used to deploy an AI pre-detection model. The AI ​​pre-detection model executes the AI ​​pre-detection-based intelligent video content tagging and display method of this application embodiment to detect and analyze video content and obtain AI pre-detection data containing detection questions associated with video timestamps. Terminal 102 is used to display visual tags and related information generated based on the detection and analysis results. These visual tags and related information can be presented based on the detection results of the AI ​​pre-detection model deployed on server 104.

[0033] The AI ​​pre-detection-based intelligent video content tagging and display method of this embodiment can be applied to scenarios such as video review, content management, and online video quality control. For example, in the video review scenario, it can help reviewers quickly locate...Problematic segments in the video; in content management scenarios, it facilitates content creators to optimize video content; in online video quality control scenarios, it helps managers discover problems in video explanations. This application embodiment uses a video review scenario as an example to illustrate the above-mentioned AI-based pre-detection intelligent labeling and display method for video content.

[0034] In the prior art, the review and management of video content often relies on manual frame-by-frame viewing to discover problems. This method is extremely inefficient, not only consuming a lot of manpower and time, but also making it difficult to guarantee the comprehensiveness and accuracy of the review when faced with massive amounts of video data. At the same time, most existing video labeling methods simply add labels to specific positions in the video, lacking dynamic correlation with video playback time, and cannot adjust the display status of the labels in real time according to the video playback progress, making it difficult for users to quickly focus on key problem positions when viewing the video, affecting the efficiency and quality of video review and management.

[0035] To solve the above problems, this embodiment provides a video content intelligent tagging and display method based on AI pre-detection running on the above-mentioned server. Please refer to Figure 2. Figure 2 is a flowchart of an optional video content intelligent tagging and display method based on AI pre-detection provided in this application embodiment. As shown in Figure 2, the video content intelligent tagging and display method based on AI pre-detection in this application embodiment specifically includes the following steps: Step S201: Obtain the AI ​​pre-detection data of the current video and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data contains at least one detection question associated with the video timestamp; Step S202: Based on a preset time merging threshold, merge multiple detection questions with adjacent timestamps into a detection question group; Step S203: During the playback of the current video, monitor the current playback time in real time, and dynamically control the display status of the visualization tags and information of the detection question group corresponding to the current playback time based on the time difference between the current playback time and the reference timestamp of the detection question group, wherein the reference timestamp of the detection question group is the start time of the first detection question in the detection question group.

[0036] Through the above steps S201 to S203, by establishing a mapping relationship between the detection problem and the video timeline, and by using a time merging threshold to intelligently group adjacent detection problems, it is possible to monitor the playback time in real time during video playback, dynamically control the visualization marking and information display of the detection problem group that precisely matches the current playback time, which avoids the interference caused by frequent switching of markings, and ensures that key problems are presented in a timely manner, thereby improving the user's perception efficiency and interactive experience of video content problems.

[0037] The following describes the AI-based pre-detection intelligent marking and display method for video content in the embodiments of this application with reference to Figure 2.

[0038] In the technical solution of step S201, AI pre-detection data of the current video is obtained, and a mapping relationship between the detection problems in the AI ​​pre-detection data and the playback timeline of the current video is established. The AI ​​pre-detection data contains at least one detection problem associated with the video timestamp. The detection problem refers to the abnormal situation that does not conform to the preset rules or standards identified by the AI ​​algorithm during the video content analysis process. Each detection problem needs to be associated with the specific location of the video and the problem type needs to be clearly defined for subsequent processing. For example: the environment is too bright / too dark; a hand raising action occurs at 0:15.

[0039] In this embodiment, AI pre-detection data is obtained by calling the getVideoDetectionDetailReq() method. AI pre-detection data is obtained by detecting and analyzing the video content through a preset AI pre-detection model, and obtaining data containing detection problems associated with the video timestamp.

[0040] The steps of how to obtain AI pre-detection data through the AI ​​pre-detection model are not specifically limited. Please refer to the relevant content in the prior art.

[0041] Based on the form in which the problem exists in the video, detection problems are divided into the following two categories: Global detection problems refer to abnormal situations that occur throughout the entire video and are not dependent on specific time points. They usually have no timestamp (i.e., badTimestamp is empty or invalid) and involve overall video attributes such as resolution and background. They usually appear in the following scenarios: environmental detection (brightness, contraband), substandard resolution, cluttered background, insufficient video duration, etc. For example: an environment that is too bright / too dark is a global detection problem.

[0042] Time point detection problems refer to abnormal situations that occur only within a specific time period of the video and need to be located to a specific time range. Unlike global detection problems, they usually contain a valid timestamp (i.e., badTimestamp contains start_time and end_time) and are associated with dynamic content such as actions and postures. They usually appear in the following scenarios: non-standard actions (such as raising a hand, lowering a head), voice stuttering, screen shaking, sudden changes in light at a specific time period, etc. For example: raising a hand at 0:15 is a time point detection problem.

[0043] As an optional embodiment, establishing a mapping relationship between the detection problem and the playback timeline of the current video includes: classifying the detection items in the AI ​​pre-detection data into global detection problems and time-point detection problems; assigning a unique identifier to each detection problem; and based on the total duration of the current video, converting the timestamp of each detection problem into a relative position percentage on the video progress bar to establish a mapping relationship. The unique identifier is a unique code assigned to each detection problem, used to distinguish different detection items and establish a mapping relationship with the video timeline, ensuring the accuracy and traceability of problem location.

[0044] In this embodiment, firstly, based on whether the detection item contains a timestamp (badTimestamp field), the AI ​​pre-detection data is classified into global detection problems and time-point detection problems.The detection items in the detection data are classified into global detection problems and time-point detection problems. Specifically: No timestamp: belongs to global detection problems (such as environment detection, resolution detection, etc.).

[0045] With timestamp: belongs to time-point detection problems (such as motion detection, pose detection, etc.).

[0046] Secondly, the detection problems are associated with the video timeline through a unique identifier (UUID), and the timestamp of each detection problem is converted into the relative position percentage on the video progress bar, thereby establishing a mapping relationship to ensure that the problem can be accurately located to the specific type (global / time point) and position (timestamp or global attribute).

[0047] According to the above technical means, by classifying the detection problems and assigning unique identifiers, and combining the total video duration to convert the timestamp into the relative position percentage on the progress bar, the accurate and standardized mapping between the detection problems and the video timeline is realized. This can clearly distinguish between global problems and problems in specific time periods, and ensure the consistency of problem location under different video durations, providing a reliable data foundation for subsequent dynamic display and interactive control.

[0048] As an optional embodiment, based on the total duration of the current video, the timestamp of each detection problem is converted into a relative position percentage on the video progress bar, including: obtaining the total duration of the current video; for each detection problem, obtaining the relative position percentage of each detection problem on the video progress bar through a preset percentage formula, wherein the relative position percentage is used to determine the rendering position of the visual marker of the detection problem on the progress bar.

[0049] In this embodiment, let the total duration of the video be T (unit: seconds), the start timestamp of the detection problem be t (unit: seconds), and the total length of the video progress bar be L (unit: pixels or percentage), then the relative position percentage P of the detection problem on the progress bar is calculated as shown in the following formula (1): (1) In practical applications, the total duration of the video T and the start timestamp of the detection problem t are input into the above formula (1) to calculate the relative position percentage P (range: 0%~100%), which represents the position percentage of the detection problem on the progress bar. It can be understood that by linearly mapping the timeline to the progress bar, the marker positions of videos with different durations can be compared.

[0050] According to the above technical means, by converting the timestamp of the detected problem into a percentage of the relative position on the progress bar based on the total video duration, the standardized positioning of the detected problem on the timeline is achieved, ensuring the comparability and consistency of the problem marker positions in videos of different durations. Simultaneously, it provides data support for the accurate rendering of visual markers on the progress bar, effectively improving the user's intuitive perception of the distribution of video problems.

[0051] In the technical solution of step S202, based on a preset time merging threshold, multiple detected problems with adjacent timestamps are merged into a single detected problem group.

[0052] In this embodiment, the time merging threshold is used to determine the critical time interval between adjacent detection issues and whether they belong to the same time group. The default value is 3000ms (3 seconds). If the timestamp difference between two detection issues is less than the threshold, they are considered to be in the same group; otherwise, they are considered to be independent groups. A detection issue group refers to a set of multiple detection issues with adjacent timestamps that meet the merging threshold. It is used to uniformly manage detection items with similar times and avoid scattered processing.

[0053] As an optional embodiment, based on the preset time merging threshold, multiple detection issues with adjacent timestamps are merged into a detection issue group, including: sorting all detection issues in ascending order according to their timestamps to obtain a detection issue list; traversing the sorted detection issue list, if the difference between the current detection issue and the base timestamp of the current detection issue group is less than the time merging threshold, then merging it into the current detection issue group; otherwise, creating a new detection issue group starting from the current detection issue.

[0054] In practice, based on a preset time merging threshold, multiple detection issues with adjacent timestamps are merged into a detection issue group, specifically including the following steps: 1. Sort the detection issues: Sort all detection issues in ascending order according to their timestamps to generate a detection issue list, ensuring the time continuity of subsequent processing.

[0055] 2. Initialize the merged group: Create an empty array mergedGroups to store the merging results, and initialize the current merged group currentGroup, whose base timestamp is the timestamp of the first detection issue.

[0056] 3. Traverse the detection issue list: Use a sliding window algorithm to traverse the sorted detection issue list, and perform the following operations for each detection issue: Calculate the difference between the timestamp of the current detection issue and the base timestamp of currentGroup.

[0057] If the difference is less than the time merging threshold: merge the current detection issue into currentGroup, and update the base timestamp of currentGroup to the earliest timestamp in the group.

[0058] If the difference is greater than or equal to the time merging threshold: store currentGroup in mergedGroups, and create a new merge group, starting the merging process again based on the current detection problem.

[0059] 4. After processing the last merge group traversal, add the unstored currentGroup to mergedGroups.

[0060] According to the above technical means, by sorting the detection problems in ascending order of timestamps and merging the detection problems with adjacent timestamps into groups based on the preset time merging threshold, it is possible to effectively integrate detection problems with similar times, avoid scattered processing, and improve the efficiency of problem management and the continuity of analysis.

[0061] The following is the actual data structure of the specific detection problem group:preCheckList: [ { time: '12.345', / / Baseline timestamp (seconds) left: 25.6, / / Progress bar position percentage rotate: false, / / Whether to rotate the display list: [ / / List of detection items in the merged group { label: '00:12', / / MM:SS format display label identity: 'uuid', / / Unique identifier detectionTypeName: 'Screen stuttering', detectionMappingRejectReason: 'Frame rate is lower than 24fps'}, / / ...more detection items]}, / / ...more merged groups]. As an optional embodiment, after processing the last merged group, it is also necessary to calculate the display attributes of the merged group. Specifically: calculate the following attributes for each merged group for subsequent visualization rendering: Time axis position (left): Calculate its relative position percentage on the progress bar based on the ratio of the merged group's base timestamp to the total video duration. The calculation formula refers to formula (1) in the above embodiment.

[0062] Rotate: The getRotateNeedIndex() method is used to determine whether the detection items in the group need to be alternately displayed above and below the timeline to avoid overlap.

[0063] Detection Item List: Stores detailed information of all detection issues in the merged group for floating prompt display.

[0064] According to the above technical means, by calculating the display attributes such as the timeline position of the merged group, the rotation mark, and the detection item list, the visual position of the issue on the progress bar can be accurately located, the alternating layout of overlapping items can be optimized, and the detection details can be completely preserved, thereby improving the readability and interaction efficiency of the video review results.

[0065] In the technical solution of step S203, during the playback of the current video, the current playback time is monitored in real time. Based on the time difference between the current playback time and the reference timestamp of the detection issue group, the display status of the visual mark and information of the detection issue group corresponding to the current playback time is dynamically controlled. In this embodiment, the reference timestamp of the detection problem group is the start time of the first detection problem in the detection problem group, used to mark the time reference of the group in the video.

[0066] As an optional embodiment, based on the time difference between the current playback time and the reference timestamp of the detection problem group, the display status of the visual markers and information of the detection problem group corresponding to the current playback time is dynamically controlled, including: obtaining the reference timestamp of the detection problem group and the current playback time; determining the time difference between the reference timestamp of the detection problem group and the current playback time using a preset time difference formula; when the time difference is less than or equal to a preset display time window, then controllingThe visual markers of the detection problem group are highlighted, and the detailed information of the detection problem group is displayed in the user interface; when the time difference is greater than the display time window, the visual markers of the detection problem group are controlled to return to normal display state, and the detailed information of the detection problem group is hidden in the user interface.

[0067] Visual markers: Interactive components that mark the location of the detection problem on the video progress bar using graphical elements (such as red bubbles).

[0068] Display time window: The effective time range of the detection problem information that the user can perceive (default 3 seconds, configurable), which is automatically hidden after it is exceeded.

[0069] In specific practice, based on the time difference between the current playback time and the reference timestamp of the detection problem group, the display state of the visual markers and information of the detection problem group corresponding to the current playback time is dynamically controlled, which specifically includes the following steps: 1. Time listening: Obtain the current playback time currentTime through the browser's native timeupdate event.

[0070] 2. Time difference calculation: Traverse all detection problem groups and calculate currentTime - item.time, where item.time is the reference timestamp).

[0071] 3. State control: If the time difference ≤ the display time window (e.g., 3 seconds): Highlight the visual marker and display detailed information about the detection problem group (e.g., cause of stuttering, time point, etc.) on the user interface.

[0072] If the time difference > the display time window: Restore the visual marker to the normal state and hide the detailed information.

[0073] The following specific examples illustrate the above scheme. Assuming the baseline timestamp of the detection problem group A is 10 seconds and the display time window is 3 seconds, then when the video plays to 10 seconds, the red bubble marker on the progress bar is highlighted, and the floating prompt displays "Stuttering: Frame rate is below 24fps"; when the video plays to 13 seconds, the bubble marker returns to the normal state, and the floating prompt is automatically hidden.

[0074] In this embodiment, the final rendering position is determined according to the implementation method of the progress bar (pixels or percentage): If the total length of the progress bar is the pixel value L, for example: L = 500 px, P = 30%, then the rendering position is determined.

[0075] If the progress bar directly uses percentages: directly use P=30% as the rendering position.

[0076] According to the above technical means, by calculating the time difference between the current playback time and the baseline timestamp of the detection problem group, and dynamically controlling the display status of the visualization markers and information according to the preset display time window, it is possible to accurately and timely highlight the detection problem group closely related to the current playback period when the user is watching the video, attract the user's attention in a highlighted form and present detailed information, while restoring normal display and hiding details during irrelevant periods to avoid information interference, thereby significantly improving...Improve user attention efficiency and interactive experience for video detection issues. Manual 9 / 14 pages 12 CN 121547612 A

[0077] In addition, to support users' refined operation of detection issues, the system provides soft deletion and recovery functions, allowing users to temporarily hide non-critical issues or correct misjudgments, while maintaining data traceability.

[0078] As an optional embodiment, in response to user operation, a specific detection issue is deleted or recovered from the detection issue group. The specific steps are as follows: obtain a preset deletion list, wherein the deletion list contains the unique identifier of the deleted detection issue; in response to the user's deletion operation on the first detection issue, add the unique identifier of the first detection issue to the deletion list, and mark the first detection issue as deleted in the user interface; in response to the user's recovery operation on the deleted second detection issue, remove the unique identifier of the second detection issue from the deletion list, and mark the second detection issue as normally displayed in the user interface.

[0079] In this embodiment, the deletion list maintains an array of unique identification codes of deleted issues for status query and recovery operations.

[0080] In practical applications, if a user accidentally deletes a critical issue A, the steps from deletion to restoration are as follows: Deletion: Click the "Delete" button for issue A, and issue A will display a strikethrough. The ID of issue A will be added to the deletion list preCheckIdsDel.

[0081] Restoration: Click the "Restore" button, and issue A will be restored to its normal state. The issue AID will be removed from the deletion list preCheckIdsDel.

[0082] According to the above technical means, by setting a deletion list containing a unique identifier for deleted detection issues, the identifier of the detection issue to be deleted can be quickly added to the list and marked as deleted when the user operates, achieving accurate deletion; at the same time, when the user needs to restore, the corresponding identifier can be removed from the list and the normal display can be restored. This flexible deletion and restoration mechanism gives users more autonomous and convenient management capabilities for detection issues, effectively improving the efficiency and experience of user interaction with detection issues.

[0083] In addition, in order to improve the efficiency of video review, the system needs to automatically generate structured rejection reason text to help the photographer quickly locate the problem. The text must include a timestamp (for point-in-time issues) and a clear description of the issue, excluding deleted detection issues.

[0084] As an optional embodiment, based on all undeleted detection issues, the rejection reason text for video review is automatically generated according to a preset structured template. The specific steps are as follows: obtain all global detection issues and point-in-time detection issues; filter out the detection issues in the deletion list from all issues; sort the remaining detection issues after filtering in ascending order according to their timestamps; format the sorted detection issues into text according to a preset template, wherein, for point-in-time issues...The detection problem is converted to MM:SS format and then concatenated with the problem description; all formatted texts are summarized to generate a complete rejection reason.

[0085] The structured template refers to a predefined text format used to unify the display of rejection reasons. An example of a rejection reason generated using it is as follows: Background environment Please select a clean environment, please re-record 00:04 When recording, please keep a certain distance from the camera, please re-record 00:31 The camera is shaking, please keep the image stable when recording 00:35 When shooting, please keep the portrait centered, sit upright, and face the camera.

[0086] In specific practice, based on the time difference between the current playback time and the baseline timestamp of the detection problem group, the display status of the visual markers and information of the detection problem group corresponding to the current playback time is dynamically controlled, specifically including the following steps: 1. Data collection: Manual 10 / 14 pages 13 CN 121547612 A Obtain two types of detection problems: allPreCheck: Global detection problem list (such as ["cluttered background", "insufficient light"]).

[0087] preCheckRecord: A list of time-point detection issues (e.g., [{"time": 4, "desc": "too close"}, {"time": 31, "desc": "camera shake"}]).

[0088] 2. Filter deleted issues: Iterate through all issues and remove those whose IDs exist in the deletion list preCheckIdsDel.

[0089] 3. Time sorting: Sort time-point issues in ascending order of timestamp, with global issues at the end by default.

[0090] 4. Template formatting: Global issues: Directly output description.

[0091] Time-point issues: Convert to MM:SS + issue description format.

[0092] 5. Generate complete rejection reason: Summarize all formatted text and generate the final result.

[0093] In this embodiment, the review rejection entry method handleReject() calls the getRejectReason() method to generate text. The main logic of data integration, filtering, sorting, and formatting is achieved through the getRejectReason() method.

[0094] Based on the above technical means, based on the detection issues that have not been deleted, the text is formatted by filtering deleted items, sorting by timestamp, and formatting with a preset template. In particular, the timestamps of the time point detection issues are standardized into MM:SS format for concatenating descriptions, ultimately generating a structured text for video review rejection reasons. This can automatically and accurately integrate issue information, making the rejection reasons clear and standardized, greatly improving the efficiency and accuracy of reason feedback in the video review process, and facilitating quick understanding and processing by reviewers.

[0095] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited by the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk), including several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0097] According to another aspect of the embodiments of this application, an AI-based video content intelligent tagging display device for implementing the above-described AI-based video content intelligent tagging display method is also provided. Please refer to Figure 3. Figure 3 is a structural block diagram of an optional AI-based pre-detection intelligent labeling display device for video content provided in an embodiment of this application. As shown in Figure 3, the device 300 may include: a data acquisition and mapping module 301, used to acquire AI pre-detection data of the current video and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data includes at least one detection question associated with the video timestamp; a question merging module 302, used to merge multiple detection questions with adjacent timestamps into a detection question group based on a preset time merging threshold; and an interactive control module 303, used to monitor the current playback time in real time during the playback of the current video, and dynamically control the display status of the visual labels and information of the detection question group corresponding to the current playback time based on the time difference between the current playback time and the reference timestamp of the detection question group, wherein the reference timestamp of the detection question group is the start time of the first detection question in the detection question group.

[0098] It should be noted that the data acquisition and mapping module 301 in this embodiment can be used to execute the above step S201, and the problem merging module 302 in this embodiment can be used to execute the above step S202. The interactive control in this embodiment...Module 303 can be used to execute the above step S203.

[0099] Regarding the AI-based pre-detection video content intelligent labeling display device in this embodiment, the specific manner in which the data acquisition and mapping module 301, the problem merging module 302, and the interaction control module 303 execute the above-mentioned AI-based pre-detection video content intelligent labeling display method has been described in detail in the embodiments related to the AI-based pre-detection video content intelligent labeling display method, and will not be elaborated here.

[0100] It can be understood that the technical solution provided in this embodiment, the various modules in the AI-based pre-detection video content intelligent labeling display device, by establishing a mapping relationship between the detection problem and the video timeline, and by using the time merging threshold to intelligently group adjacent detection problems, can monitor the playback time in real time during video playback, dynamically control the visualization labeling and information display of the detection problem group that accurately matches the current playback period, which avoids the interference caused by frequent label switching, and ensures that key problems are presented in a timely manner, thereby improving the user's perception efficiency and interactive experience of video content problems.

[0101] As an optional embodiment, the above-mentioned device further includes: a detection point management module, used to delete or restore a specific detection problem from the detection problem group in response to user operation, the specific steps being: obtaining a preset deletion list, wherein the deletion list contains a unique identifier of the deleted detection problem; in response to the user's deletion operation on the first detection problem, adding the unique identifier of the first detection problem to the deletion list, and marking the first detection problem as deleted in the user interface; in response to the user's restoration operation on the deleted second detection problem, removing the unique identifier of the second detection problem from the deletion list, and marking the second detection problem as normally displayed in the user interface.

[0102] According to the above technical means, by setting a deletion list containing the unique identifier of the deleted detection problem, the identifier of the detection problem to be deleted can be quickly added to the list and marked as deleted in the user operation, achieving accurate deletion; at the same time, when the user needs to restore, the corresponding identifier can be removed from the list and the normal display can be restored. This flexible deletion and restoration mechanism gives users more autonomous and convenient management capabilities for detection problems, effectively improving the efficiency and experience of user interaction with detection problems.

[0103] As an optional embodiment, the above-mentioned device further includes: a rejection reason generation module, used to automatically generate rejection reason text for video review based on all undeleted detection issues and according to a preset structured template. The specific steps are: obtaining all global detection issues and time-point detection issues; filtering out detection issues in the deletion list from all issues; sorting the remaining detection issues after filtering in ascending order according to their timestamps; and sorting the sorted detection issues...The text is formatted according to a preset template. For time point detection issues, the timestamp is converted to MM:SS format and then concatenated with the issue description. All formatted texts are summarized to generate a complete rejection reason.

[0104] According to the above technical means, based on the detection issues that have not been deleted, by filtering the deletion items, sorting by timestamp and formatting the text with a preset template, especially by standardizing the timestamp of the time point detection issues to MM:SS format and concatenating the description, a structured video review rejection reason text is finally generated. This can automatically and accurately integrate the issue information, making the rejection reason explanation clear and the content standardized, greatly improving the efficiency and accuracy of the reason feedback in the video review process, and facilitating the reviewers to quickly understand and process it.

[0105] In addition to the above modules, the device in this embodiment may also include modules that execute any method in any of the embodiments of the AI ​​pre-detection video content intelligent tagging display method.

[0106] It should be noted here that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above-mentioned module, as part of the device, can run in the hardware environment that implements the method shown in FIG1. ​​It can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0107] According to another aspect of the embodiments of this application, an electronic device for implementing the above-mentioned AI pre-detection-based intelligent tagging display method for video content is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0108] According to another embodiment of this application, an electronic device is also provided. Please refer to FIG4. FIG4 is a structural block diagram of an optional electronic device provided in the embodiments of this application. As shown in FIG4, the electronic device may include: a processor 1501, a communication interface 1502, a memory 1503, and a communication bus 1504, wherein the processor 1501, the communication interface 1502, and the memory 1503 communicate with each other through the communication bus 1504.

[0109] The memory 1503 is used to store computer programs; the processor 1501 is used to execute the program stored in the memory 1503, and implement the following steps: Step S201, acquire the AI ​​pre-detection data of the current video, and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data contains at least one detection question associated with the video timestamp; Step S202, based on a preset time merging threshold, merge multiple detection questions with adjacent timestamps into a detection question group; Step S203, during the playback of the current video, monitor the current playback time in real time, and based on the current playback time...The time difference with the reference timestamp of the detection problem group is used to dynamically control the display status of the visual markers and information of the detection problem group corresponding to the current playback time. The reference timestamp of the detection problem group is the start time of the first detection problem in the detection problem group.

[0110] It can be understood that the processor of the electronic device, by establishing a mapping relationship between the detection problem and the video timeline and using a time merging threshold to intelligently group adjacent detection problems, can monitor the playback time in real time during video playback and dynamically control the display of the visual markers and information of the detection problem group that accurately matches the current playback period. This avoids the interference caused by frequent switching of markers and ensures that key problems are presented in a timely manner, thereby improving the user's perception efficiency and interactive experience of video content problems.

[0111] Optionally, in this embodiment, the above-mentioned communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or one type of bus. The communication interface is used for communication between the above-mentioned electronic device and other devices.

[0112] The memory may include random access memory (RAM), and may also include non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0113] The above-mentioned processor may be a general-purpose processor, and may include, but is not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it may also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0114] Embodiments of this application also provide a computer-readable storage medium, the storage medium including a stored program, wherein,The program executes the method steps of the above method embodiments during runtime.

[0115] Optionally, in this embodiment, the above storage medium may include, but is not limited to, various media capable of storing program code such as USB flash drive, ROM, RAM, mobile hard disk, magnetic disk or optical disk.

[0116] The sequence numbers of the above embodiments of this application are merely for description and do not represent the superiority or inferiority of the embodiments.

[0117] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers or network devices, etc.) to execute all or part of the steps of the methods of the various embodiments of this application.

[0118] In the above embodiments of this application, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0121] In addition, the functional units in the various embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units.

[0122] The above are merely preferred embodiments of this application. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application. Specification 14 / 14 pages 17 CN 121547612 A Figure 1 Figure 2 DescriptionSpecification附图1 / 2页18 CN 121547612 A图3图4说明书附图2 / 2页19 CN 121547612 A {HARTEND-26017-HKSPT / 02503908v1}摘要本申请涉及前端视频处理与人工智能应用相结合的技术领域,具体涉及一种基于AI预检测的视频内容智能标注与显示方法及装置。通过建立检测问题与视频时间线之间的映射关系,并使用时间合并阈值对相邻检测问题进行智能分组,本申请能够在视频播放过程中实时监控播放时间,并动态控制与当前播放周期精确匹配的检测问题组的可视化标注和信息显示。这不仅避免了标记频繁切换所造成的干扰,还确保了关键问题能够及时呈现,从而提高了用户的感知效率和交互体验video content issues.

Claims

1. A method for intelligent labeling and displaying video content based on AI pre-detection, characterized in that, include: Acquire AI pre-detection data of the current video and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video, wherein the AI ​​pre-detection data contains at least one detection question associated with the video timestamp; Based on a preset time merging threshold, multiple detection issues with adjacent timestamps are merged into a single detection issue group. During the playback of the current video, the current playback time is monitored in real time. Based on the time difference between the current playback time and the reference timestamp of the detection problem group, the display status of the visual markers and information of the detection problem group corresponding to the current playback time is dynamically controlled. The reference timestamp of the detection problem group is the start time of the first detection problem in the detection problem group.

2. The video content intelligent tagging and display method based on AI pre-detection according to claim 1, characterized in that, Based on a preset time merging threshold, multiple detection questions with adjacent timestamps are merged into a single detection question group, including: Sort all detection issues in ascending order according to their timestamps to obtain a list of detection issues; Traverse the sorted list of detection issues. If the difference between the current detection issue and the baseline timestamp of the current detection issue group is less than the time merging threshold, then merge it into the current detection issue group; otherwise, create a new detection issue group starting from the current detection issue.

3. The intelligent labeling and display method for video content based on AI pre-detection according to claim 1, characterized in that, Establishing a mapping relationship between the detection problem and the playback timeline of the current video includes: The detection items in the AI ​​pre-detection data are classified into global detection problems and time-point detection problems; Assign a unique identifier to each detection question; Based on the total duration of the current video, the timestamp of each detected problem is converted into a relative position percentage on the video progress bar, and the mapping relationship is established.

4. The intelligent tagging and display method for video content based on AI pre-detection according to claim 3, characterized in that, Based on the total duration of the current video, the timestamp of each detected issue is converted into a relative percentage position on the video progress bar, including: Get the total duration of the current video; For each detection problem, the relative position percentage of each detection problem on the video progress bar is obtained through a preset percentage formula, wherein the relative position percentage is used to determine the rendering position of the visual marker of the detection problem on the progress bar.

5. The intelligent labeling and display method for video content based on AI pre-detection according to claim 1, characterized in that, Based on the time difference between the current playback time and the baseline timestamp of the detected problem group, the display status of the visual markers and information of the detected problem group corresponding to the current playback time is dynamically controlled, including: Obtain the baseline timestamp of the detected problem group and the current playback time; The time difference is determined by using a preset time difference formula between the baseline timestamp of the detected problem group and the current playback time; When the time difference is less than or equal to the preset display time window, the visual marker of the detected problem group is highlighted, and the detailed information of the detected problem group is displayed in the user interface; When the time difference is greater than the display time window, the visual markers of the detected problem group are restored to normal display status, and the detailed information of the detected problem group is hidden in the user interface.

6. The intelligent labeling and display method for video content based on AI pre-detection according to claim 1, characterized in that, The method further includes: in response to a user operation, deleting or restoring a specific detection issue from the detection issue group, specifically through the following steps: Obtain a preset deletion list, wherein the deletion list contains unique identifiers of deleted detection issues; In response to the user's deletion operation of the first detection issue, the unique identifier of the first detection issue is added to the deletion list, and the first detection issue is marked as deleted in the user interface; In response to the user's restore operation for the deleted second detection issue, the unique identifier of the second detection issue is removed from the deletion list, and the second detection issue is marked as a normal display status in the user interface.

7. The intelligent tagging and display method for video content based on AI pre-detection according to claim 6, characterized in that, The method further includes: based on all the detection issues that have not been deleted, automatically generating rejection reason text for video review according to a preset structured template, the specific steps of which are as follows: Retrieve all global detection issues and time-point detection issues; Filter out the detection issues from the deletion list from all issues; The remaining detection questions after filtering are sorted in ascending order according to their timestamps; The sorted detection issues are formatted into text according to a preset template. For time-point detection issues, their timestamps are converted to MM:SS format and then concatenated with the issue description. Summarize all formatted text to generate a complete rejection reason.

8. A video content intelligent labeling and display device based on AI pre-detection, characterized in that, include: The data acquisition and mapping module is used to acquire AI pre-detection data of the current video and establish a mapping relationship between the detection questions in the AI ​​pre-detection data and the playback timeline of the current video. The AI ​​pre-detection data includes at least one detection question associated with the video timestamp. The issue merging module is used to merge multiple detection issues with adjacent timestamps into a single detection issue group based on a preset time merging threshold. The interactive control module is used to monitor the current playback time in real time during the playback of the current video, and dynamically control the display status of the visual markers and information of the detection problem group corresponding to the current playback time based on the time difference between the current playback time and the reference timestamp of the detection problem group. The reference timestamp of the detection problem group is the start time of the first detection problem in the detection problem group.

9. An electronic device comprising a processor, a communication interface, a memory, and a communication bus, wherein, The processor, the communication interface, and the memory communicate with each other via the communication bus, characterized in that... The memory is used to store computer programs; The processor is configured to execute the AI-based pre-detection video content intelligent tagging display method according to any one of claims 1 to 7 by running the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the AI-based pre-detection video content intelligent tagging display method according to any one of claims 1 to 7 when running.

Images