An interception system performance test method, device, equipment and storage medium

Abstract

The application discloses an interception system performance test method and device, equipment and a storage medium, and relates to the technical field of security broadcasting. The method comprises the following steps: acquiring pictures of an electronic display screen collected by a camera at a high-frequency sampling rate, so as to obtain a plurality of picture frames corresponding to each display period of the electronic display screen; the electronic display screen adopts an artificial intelligence interception system, which is used for automatically intercepting and displaying a preset safety picture when it is detected that a played picture is a rule violation picture; according to the brightness and integrity of the picture frames, an effective reference frame corresponding to each display period is determined; the effective reference frame is compared with the preset safety picture, and a performance test result of the interception system is generated according to a comparison result and current playing materials of the electronic display screen. The pictures of the electronic display screen are collected at a high-frequency sampling rate, and the effective reference frame is screened according to the brightness and integrity of the picture frames for subsequent comparison, so that misjudgment caused by quality problems of the picture frames is avoided, and the accuracy of performance test is improved.

Description

Technical Field

[0001] This invention relates to the field of secure broadcast control technology, and in particular to a method, apparatus, equipment and storage medium for testing the performance of an interception system. Background Technology

[0002] Currently, electronic displays are commonly used in public places such as commercial complexes or exhibition halls to play content. Traditional solutions for the safe control of electronic displays (such as LED screens (light-emitting diodes)) rely heavily on manual monitoring, which is inefficient and can easily cause visual fatigue during long periods of observation, leading to missed or misreading. Furthermore, it cannot provide quantitative data accurate to the frame level, meaning that manual judgment can only record the results and cannot determine the duration of exposure of illegal images.

[0003] In related technologies, the electronic display screen security broadcast control system mainly relies on an AI-based interception system to determine and intercept illegal content in real time. Therefore, how to achieve efficient and accurate performance testing of the interception system is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method, apparatus, device, and storage medium for testing the performance of an interception system, which can avoid misjudgments caused by image frame quality issues and improve the accuracy of performance testing. The specific solution is as follows: Firstly, this application discloses a method for testing the performance of an interception system, including: The camera captures images from the electronic display screen at a high-frequency sampling rate, resulting in multiple image frames corresponding to each display cycle. The electronic display screen employs an artificial intelligence interception system to automatically intercept and display a preset safe image when the displayed image is detected as an illegal image. Based on the brightness and integrity of the image frames, determine the effective reference frame corresponding to each display cycle; The effective reference frame is compared with the preset security screen, and the performance test results of the interception system are generated based on the comparison results and the currently playing material on the electronic display screen.

[0005] Optionally, determining the effective reference frame for each display cycle based on the brightness and integrity of the image frame includes: Calculate the global pixel brightness average of the image frame, and calculate the integrity of the image frame using an image algorithm; Based on the global pixel brightness average and the integrity, a validity score is determined for each image frame; The image frame with the highest validity score among all image frames corresponding to the current display period is taken as the valid reference frame.

[0006] Optionally, comparing the valid reference frame with a preset security image, and generating performance test results for the interception system based on the comparison results and the currently playing material on the electronic display screen, includes: When the currently playing material is a video material generated based on a first number of illegal segments, if the valid reference frame does not hit the preset safe screen, the valid reference frame is retained. After the current playback material is played on the electronic display screen, all the saved valid reference frames are deduplicated to obtain the number of times the valid reference frames did not hit the preset safety screen, and this number is used as the second number. The interception rate of the interception system is calculated using the interception rate calculation formula based on the first number and the second number.

[0007] Optionally, comparing the valid reference frame with a preset security image, and generating performance test results for the interception system based on the comparison results and the currently playing material on the electronic display screen, includes: When the current playback material on the electronic display screen is a video material generated based on a third number of normal segments, if the valid reference frame hits the preset safety screen, then the valid reference frame is retained. After the current playback material is played on the electronic display screen, all the saved valid reference frames are deduplicated to obtain the number of times the valid reference frames hit the preset safe screen, and this number is used as the fourth number. The false alarm rate of the interception system is calculated using the false alarm rate calculation formula based on the third number and the fourth number.

[0008] Optionally, retaining the valid reference frame includes: Save the valid reference frame and the timestamp corresponding to the valid reference frame to obtain the set of reference frames corresponding to the currently playing material; The process of deduplicating all saved valid reference frames includes: Based on the timestamp difference and the difference threshold between different frames in the reference frame set, the reference frame set is deduplicated.

[0009] Optionally, when the electronic display screen is a light-emitting diode display screen, the sampling rate of the camera is greater than or equal to a first preset sampling rate.

[0010] Optionally, when the electronic display screen is a liquid crystal display screen, the sampling rate of the camera is greater than or equal to the second preset sampling rate.

[0011] Secondly, this application discloses an interception system performance testing device, comprising: The acquisition module is used to acquire images from the electronic display screen captured by the camera at a high-frequency sampling rate, resulting in multiple image frames corresponding to each display cycle of the electronic display screen; the electronic display screen adopts an artificial intelligence interception system, which is used to automatically intercept and display a preset safe image when the played image is detected to be an illegal image; The effective reference frame determination module is used to determine the effective reference frame corresponding to each display cycle based on the brightness and integrity of the image frame. The test result generation module is used to compare the effective reference frame with the preset security screen, and generate the performance test results of the interception system based on the comparison results and the currently playing material on the electronic display screen.

[0012] Thirdly, this application discloses an electronic device, including: Memory, used to store computer programs; A processor is used to execute the computer program to implement the aforementioned interception system performance testing method.

[0013] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned interception system performance testing method.

[0014] In this application, a camera captures images from an electronic display screen at a high-frequency sampling rate, resulting in multiple image frames corresponding to each display cycle. The electronic display screen employs an artificial intelligence interception system to automatically intercept and display a preset safe image when the displayed image is detected as an invalid image. Based on the brightness and integrity of the image frames, a valid reference frame is determined for each display cycle. The valid reference frame is compared with the preset safe image, and based on the comparison result and the currently playing material on the electronic display screen, a performance test result for the interception system is generated. Therefore, by capturing images from the electronic display screen at a high-frequency sampling rate, a sufficiently dense sampling point coverage of the effective light-emitting period of the electronic display screen is ensured, avoiding the acquisition of invalid image frames. Furthermore, by filtering valid reference frames based on their brightness and integrity for subsequent comparison, misjudgments due to image frame quality issues are avoided, improving the accuracy of the performance test. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0016] Figure 1A flowchart of a performance testing method for an interception system provided in this application; Figure 2 A flowchart of a specific interception rate testing method provided in this application; Figure 3 A flowchart of a specific false alarm rate testing method provided in this application; Figure 4 This application provides a schematic diagram of the structure of an interception system performance testing device; Figure 5 This application provides a structural diagram of an electronic device. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In existing technologies, secure broadcast control systems for electronic displays mainly rely on AI-based interception systems to identify and block inappropriate content in real time. Therefore, how to achieve efficient and accurate performance testing of the interception system is a pressing technical problem that needs to be solved. To overcome the above technical problem, this application proposes a performance testing method for an interception system, which can achieve efficient and accurate performance testing of the interception system without intruding on the broadcast control box.

[0019] This application discloses a method for testing the performance of an interception system. (See also...) Figure 1 As shown, the method may include the following steps: Step S11: The camera captures images from the electronic display screen at a high-frequency sampling rate, resulting in multiple image frames corresponding to each display cycle. The electronic display screen employs an artificial intelligence interception system to automatically intercept and display a preset safe image when the displayed image is detected to be an illegal image.

[0020] First, multiple image frames corresponding to each display cycle of the electronic display screen are acquired. These image frames are obtained by the camera capturing the screen's image at a high-frequency sampling rate. It's understandable that because the electronic display screen uses a progressive scan method—meaning the screen doesn't display all pixels simultaneously but scans and lights them up line by line—and there's a blanking time, a very short time during line transitions to prevent ghosting, one complete frame on the electronic display screen constitutes one display cycle.

[0021] Given the aforementioned physical characteristics of electronic displays, using low-frequency sampling rates (such as 30fps) can easily result in scanning black bars or image banding, leading to incomplete comparison reference images. Specifically, if the shutter speed is much lower than the screen's refresh rate, and the camera's shutter opening time (camera exposure time) is shorter than a complete display cycle of the screen, the captured image will exhibit obvious defects. For example, when the camera shutter opens, it may only capture the state of the screen up to the 10th line, while the 11th line is not yet lit; or it may capture the blanking period, resulting in photos with black horizontal stripes, image tearing, color banding, or uneven brightness. Therefore, this embodiment employs high-speed sampling (such as 240fps, shortening the sampling period to 4.16ms). By capturing with a high-frequency shutter, the originally long display cycle can be subdivided into multiple tiny time slices, ensuring that there are sufficiently dense sampling points covering the effective light-emitting period of the electronic display at any given time.

[0022] In specific implementations, when the electronic display screen is a light-emitting diode (LED) display screen, the sampling rate of the camera is greater than or equal to a first preset sampling rate; when the electronic display screen is a liquid crystal display (LCD) display screen, the sampling rate of the camera is greater than or equal to a second preset sampling rate; the second preset sampling rate is less than the first preset sampling rate. The first preset sampling rate can be 240 fps, and the second preset sampling rate can be 60 fps; that is, for LED screens, the high-speed camera should sample at a rate of 240 fps or higher, and for LCD screens, the high-speed camera should sample at a rate of 60 fps or higher.

[0023] The aforementioned electronic display screen employs an artificial intelligence (AI)-based interception system. For example, a built-in large model is added to the front end of the broadcast control system. This large model is a trained model. When the broadcast content contains illegal content, the protection terminal will display a preset safe image, that is, output a preset, safe protective image (such as a solid color background or a specific safety prompt image) on the display screen to replace the display of the illegal content. Furthermore, it should be noted that the image sensor in the aforementioned camera uses a global shutter. Because the electronic display screen itself emits light line by line, the global shutter ensures that the state of all pixels on the entire screen is captured simultaneously within the same microsecond.

[0024] Step S12: Determine the effective reference frame for each display cycle based on the brightness and integrity of the image frame.

[0025] Since the acquired high-frequency video stream inevitably contains incomplete frames during the blanking period, i.e. invalid frames, these image frames cannot be used for subsequent comparative analysis. Therefore, logical alignment is required, i.e., deleting incomplete frames or low-quality image frames, and the remaining ones are the valid reference frames. In the preferred embodiment, the frame with the best brightness and integrity is used as the above-mentioned valid reference frame, i.e., one display cycle corresponds to one valid reference frame.

[0026] In some embodiments, determining the effective reference frame for each display cycle based on the brightness and integrity of the image frame includes: calculating the global pixel brightness average of the image frame and calculating the integrity of the image frame using an image algorithm; determining the effectiveness score of each image frame based on the global pixel brightness average and the integrity; and selecting the image frame with the highest effectiveness score among all image frames corresponding to the current display cycle as the effective reference frame. It is understood that if the image frame is in the blanking period, and the LEDs of the electronic display screen are in a non-emitting or low-energy state, the overall average brightness of the captured frame will be significantly lower than that of a valid frame when all energy is released; the average pixel value of the entire image frame will be lower than a threshold, thus it is judged as a fragmented frame and discarded. Furthermore, it should be noted that the above image frame only includes the effective display area of ​​the electronic display screen; if the image frame includes a background image in addition to the effective display area of ​​the electronic display screen, then the calculation of the global pixel brightness average of the image frame is the calculation of the global pixel brightness average of the effective display area of ​​the electronic display screen. The integrity of an image frame can be determined using edge detection and frequency domain analysis to identify large areas of horizontal black scanning lines. The absence of such lines indicates an intact image. Brightness uniformity can be assessed by calculating the variance of pixel brightness within the image. Frames with the smallest variance (minimal difference between light and dark areas) and the highest mean (brightest overall) demonstrate the best brightness performance. Then, combining brightness and integrity using a weighted summation method—pre-assigning weights to brightness and integrity—to calculate the validity score of the image frame, the image with the most complete pixel matrix and the most uniform brightness is selected as the valid baseline frame for subsequent interception comparisons. These operations remove scan line interference, resulting in aligned valid baseline frames and preventing misjudgments due to image frame quality issues.

[0027] Step S13: Compare the effective reference frame with the preset security screen, and generate the performance test results of the interception system based on the comparison results and the currently playing material on the electronic display screen.

[0028] The identified valid reference frames are compared with preset safety screens. If the valid reference frame contains or is the same as the preset safety screen, the interception system can be considered to have detected a violation and blocked it. The performance testing of the aforementioned interception system includes accuracy and false alarm rate tests. Thus, high-speed sampling effectively solves the problem of incomplete image capture caused by the scanning time of electronic screens, ensuring the authenticity of the test base data and accurately capturing momentary missed or false blocks. The entire process requires no manual intervention and supports long-term cyclical testing of massive amounts of material. Furthermore, it eliminates human interference factors, ensuring objective detection data and providing a reliable basis for optimizing AI interception algorithms.

[0029] In some embodiments, comparing the valid reference frame with a preset security screen and generating a performance test result of the interception system based on the comparison result and the currently playing material on the electronic display screen includes: when the currently playing material is a video material generated based on a first number of violation segments, if the valid reference frame does not hit the preset security screen, then the valid reference frame is retained; after the electronic display screen finishes playing the currently playing material, all the saved valid reference frames are deduplicated to obtain the number of times the valid reference frame does not hit the preset security screen, and this number is used as a second number; based on the first number and the second number, the interception rate of the interception system is calculated using the interception rate calculation formula.

[0030] For example Figure 2 The following is a specific interception rate testing process: 1. Control the LED screen to cycle through M (i.e., the first number mentioned above) illegal materials. The playback control display screen is determined by the AI ​​interception system to determine whether it is illegal; if it is determined to be illegal, a preset safe screen is displayed; if it is not determined, it is displayed normally.

[0031] 2. Use a 240fps camera to capture the LED screen image in real time at 240fps. 240fps (sampling period 4.16ms) can effectively cover the LED refresh cycle, avoid interference from the line scan blanking period, and ensure the acquisition of frame images of the complete pixel matrix.

[0032] 3. Data conversion: This involves converting the video stream into single-frame images and recording the timestamp corresponding to each image frame. Specifically, the image frames can be named using the timestamps.

[0033] 4. Compare the valid reference frame with the standard preset safe image. If they match (meaning the interception was successful), no further action is taken. If they do not match (meaning the interception failed), the image is saved. It's understandable that since all currently played content is inappropriate, the AI ​​interception system should intercept all of it and display the preset safe image on the LED screen. Therefore, the selected valid reference frame should also be the preset safe image; if the valid reference frame is not the preset safe image, it indicates that the AI ​​interception system has failed.

[0034] 5. Deduplication: This involves deduplicating the saved valid reference frames to obtain the number of times the valid reference frames failed to hit the preset safety screen, which is also the number N of the unblocked violation material (i.e., the second number mentioned above). When testing the interception rate, multiple violation materials are played, and only the violation materials are played. If the valid reference frames do not hit the preset safety screen, it indicates that no violation was detected. The timestamp deduplication algorithm eliminates duplicate statistics, making the data more objective.

[0035] 6. Formula calculation: Interception rate = (M – N) / M 100%.

[0036] The retention of the valid reference frame includes: saving the valid reference frame and its corresponding timestamp to obtain the reference frame set corresponding to the currently playing material; correspondingly, the deduplication process for all saved valid reference frames includes: performing deduplication on the reference frame set based on the timestamp difference between different frames in the reference frame set and the difference threshold. That is, the deduplication logic is implemented using a timestamp window, because the same violating material may generate multiple unblocked consecutive violating frames during the loop playback period (e.g., lasting 5 seconds). Therefore, by judging the timestamp difference between adjacent valid reference frames, if the difference is less than the difference threshold (which can be a single material playback duration threshold), it is considered as the same missed event for the same material and merged into one; if the difference is greater than the threshold, it is considered a new test round. Furthermore, image similarity comparison can be used to further ensure the rigor of deduplication; that is, if the timestamp difference between two valid reference frames is less than the difference threshold, but the similarity between these two valid reference frames is lower than the similarity threshold (i.e., very dissimilar), both can be retained.

[0037] In some embodiments, comparing the valid reference frame with a preset security screen and generating a performance test result of the interception system based on the comparison result and the currently playing material on the electronic display screen includes: when the currently playing material on the electronic display screen is a video material generated based on a third number of normal segments, if the valid reference frame hits the preset security screen, then the valid reference frame is retained; after the electronic display screen finishes playing the currently playing material, all the saved valid reference frames are deduplicated to obtain the number of times the valid reference frame hits the preset security screen, and this number is used as a fourth number; based on the third number and the fourth number, the false alarm rate of the interception system is calculated using the false alarm rate calculation formula.

[0038] For example Figure 3 The following is a specific test procedure for false positive rate (false intercept rate): 1. Control the LED screen to cycle through S (i.e., the third number mentioned above) normal content. The playback control display is determined by the AI ​​interception system to determine whether there is a violation; if a violation is determined, a preset safe screen is displayed; if no violation is determined, normal display is performed.

[0039] 2. Use a 240fps camera to capture the LED screen image in real time. 240fps (sampling period ~4.16ms) can effectively cover the LED refresh cycle, avoid interference from the line scan blanking period, and ensure the acquisition of frame images of the complete pixel matrix.

[0040] 3. Data conversion: This involves converting the video stream into single-frame images and recording the timestamp corresponding to each image frame. Specifically, the image frames can be named using the timestamps.

[0041] 4. Compare the valid reference frame with the standard preset safety screen. If they do not match the preset safety screen (indicating normal display), no action is taken; if they match the preset safety screen (indicating false blocking), the image is saved. It's understandable that since the currently playing content is normal, the AI ​​blocking system should not intercept it. Therefore, the selected valid reference frame should be a source image, not a preset safety screen. If a preset safety screen exists within the valid reference frame, it indicates a false blocking by the AI ​​blocking system.

[0042] 5. Deduplication: Deduplication is performed on all saved valid reference frames to obtain the number of times a valid reference frame hits the preset security screen. That is, for images with consecutive timestamps, only one image within that consecutive time period is kept, and the rest are deleted. The number of false interceptions A (i.e., the fourth number mentioned above) is calculated.

[0043] 7. Formula calculation: False interception rate = A / S 100%.

[0044] As can be seen, by employing high-speed physical sampling at 240fps, the LED display cycle is subdivided into microsecond-level temporal domains. The algorithm automatically eliminates invalid frames during the line scan blanking period, extracting only valid reference frames with fully released pixel energy for the judgment process. This eliminates false alarms caused by the display refresh characteristics at the physical source. The testing process is upgraded from manual verification to a fully automated, zero-intervention closed loop, increasing the daily test material throughput of a single device by more than 10 times. It achieves accurate and automated quantitative evaluation of secure broadcast control performance, replacing manual evaluation of long-term, large-sample-volume secure broadcast control performance, improving testing efficiency and reducing labor costs; furthermore, through precise graphic comparison and deduplication algorithms, the accuracy and false alarm rate calculations are improved.

[0045] This application employs a purely external optical acquisition scheme for performance testing, rather than detecting data from the playback display screen. Therefore, it eliminates the need for a control box and adapts to different software interfaces. It is completely decoupled from the control box under test (hardware, operating system, network environment), allowing full-function testing to be completed without installing any software packages, drivers, or data tracking software on the device under test. This enables plug-and-play testing; regardless of internal changes to the device under test, standardized testing can be performed immediately as long as there is screen output, significantly improving the efficiency of cross-product line test deployment. Furthermore, the accuracy of the test results is not limited by the display medium (LED / LCD).

[0046] As can be seen from the above, this embodiment uses a high-frequency sampling rate to collect images from the electronic display screen, ensuring that there are sufficiently dense sampling points covering the effective light-emitting period of the electronic display screen at any given time, thus avoiding the collection of invalid image frames. Furthermore, valid reference frames are selected based on the brightness and integrity of the image frames for subsequent comparison, avoiding misjudgments caused by image frame quality issues and improving the accuracy of performance testing. The entire testing process is completed automatically, which can significantly improve the efficiency of interception system testing.

[0047] Accordingly, this application also discloses a performance testing device for an interception system, see [link to relevant documentation]. Figure 4 As shown, the device includes: The acquisition module 11 is used to acquire images of the electronic display screen captured by the camera at a high-frequency sampling rate, resulting in multiple image frames of the electronic display screen corresponding to each display cycle; the electronic display screen adopts an artificial intelligence interception system, which is used to automatically intercept and display a preset safe image when the played image is detected to be an illegal image; The effective reference frame determination module 12 is used to determine the effective reference frame corresponding to each display cycle based on the brightness and integrity of the image frame. The test result generation module 13 is used to compare the effective reference frame with the preset security screen, and generate the performance test results of the interception system based on the comparison results and the currently playing material on the electronic display screen.

[0048] As can be seen, this embodiment uses a high-frequency sampling rate to capture images from the electronic display screen, ensuring that there are sufficiently dense sampling points covering the effective light-emitting period of the electronic display screen at any given time, thus avoiding the acquisition of invalid image frames. Furthermore, valid reference frames are selected based on the brightness and integrity of the image frames for subsequent comparison, avoiding misjudgments caused by image frame quality issues and improving the accuracy of performance testing. The entire testing process is completed automatically, which can significantly improve the efficiency of interception system testing.

[0049] In some specific embodiments, the valid reference frame determination module 12 may specifically include: The calculation unit is used to calculate the global pixel brightness average of the image frame and to calculate the integrity of the image frame using an image algorithm; The validity evaluation unit is used to determine the validity score of each image frame based on the global pixel brightness average and the integrity. The effective reference frame determination unit is used to select the image frame with the highest validity score among all image frames corresponding to the current display cycle as the effective reference frame.

[0050] In some specific embodiments, the test result generation module 13 may specifically include: The effective reference frame retention unit is used to retain the effective reference frame if the effective reference frame does not hit the preset safety screen when the currently playing material is a material video generated based on a first number of illegal segments. The deduplication unit is used to perform deduplication processing on all the saved valid reference frames after the current playback material has finished playing on the electronic display screen, to obtain the number of times the valid reference frames did not hit the preset safety screen, and to use it as a second number. An interception rate calculation unit is used to calculate the interception rate of the interception system based on the first number and the second number using an interception rate calculation formula.

[0051] In some specific embodiments, the test result generation module 13 may specifically include: The effective reference frame retention unit is used to retain the effective reference frame if the effective reference frame hits the preset safety screen when the current playback material on the electronic display screen is a video material generated based on a third number of normal segments. The deduplication unit is used to deduplicate all the saved valid reference frames after the electronic display screen finishes playing the current playback material, to obtain the number of times the valid reference frames hit the preset safety screen, and to use it as the fourth number. The false alarm rate calculation unit is used to calculate the false alarm rate of the interception system based on the third number and the fourth number using the false alarm rate calculation formula.

[0052] In some specific embodiments, the unit is used to store the valid reference frame and the timestamp corresponding to the valid reference frame, so as to obtain the reference frame set corresponding to the currently playing material; The deduplication unit is used to perform deduplication processing on the reference frame set based on the timestamp difference and the difference threshold between different frames in the reference frame set.

[0053] In some specific embodiments, when the electronic display screen is a light-emitting diode display screen, the sampling rate of the camera is greater than or equal to a first preset sampling rate.

[0054] In some specific embodiments, when the electronic display screen is a liquid crystal display screen, the sampling rate of the camera is greater than or equal to a second preset sampling rate.

[0055] Furthermore, this application also discloses an electronic device, see [link to relevant documentation]. Figure 5 As shown, the content in the figure should not be considered as any limitation on the scope of use of this application.

[0056] Figure 5 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the interception system performance testing method disclosed in any of the foregoing embodiments.

[0057] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0058] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223 including image frames, etc., and the storage method can be temporary storage or permanent storage.

[0059] The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system 221 can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the interception system performance testing method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0060] Furthermore, this application also discloses a computer storage medium storing computer-executable instructions. When the computer-executable instructions are loaded and executed by a processor, they implement the interception system performance testing method steps disclosed in any of the foregoing embodiments.

[0061] Furthermore, embodiments of this application also disclose a computer program product, including a computer program that, when executed by a processor, implements the interception system performance testing method steps disclosed in any of the foregoing embodiments.

[0062] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0063] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0064] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0065] The above provides a detailed description of the interception system performance testing method, apparatus, device, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for testing the performance of an interception system, characterized in that, include: The camera captures images from the electronic display screen at a high-frequency sampling rate, resulting in multiple image frames corresponding to each display cycle. The electronic display screen uses an artificial intelligence interception system to automatically intercept and display a preset safe screen when it detects that the displayed screen is an illegal screen. Based on the brightness and integrity of the image frames, determine the effective reference frame corresponding to each display cycle; The effective reference frame is compared with the preset security screen, and the performance test results of the interception system are generated based on the comparison results and the currently playing material on the electronic display screen.

2. The interception system performance testing method according to claim 1, characterized in that, The step of determining the effective reference frame for each display cycle based on the brightness and integrity of the image frame includes: Calculate the global pixel brightness average of the image frame, and calculate the integrity of the image frame using an image algorithm; Based on the global pixel brightness average and the integrity, a validity score is determined for each image frame; The image frame with the highest validity score among all image frames corresponding to the current display period is taken as the valid reference frame.

3. The interception system performance testing method according to claim 1, characterized in that, The step of comparing the effective reference frame with the preset security image, and generating performance test results for the interception system based on the comparison results and the currently playing material on the electronic display screen, includes: When the currently playing material is a video material generated based on a first number of illegal segments, if the valid reference frame does not hit the preset safe screen, the valid reference frame is retained. After the current playback material is played on the electronic display screen, all the saved valid reference frames are deduplicated to obtain the number of times the valid reference frames did not hit the preset safety screen, and this number is used as the second number. The interception rate of the interception system is calculated using the interception rate calculation formula based on the first number and the second number.

4. The interception system performance testing method according to claim 1, characterized in that, The step of comparing the effective reference frame with the preset security image, and generating performance test results for the interception system based on the comparison results and the currently playing material on the electronic display screen, includes: When the current playback material on the electronic display screen is a video material generated based on a third number of normal segments, if the valid reference frame hits the preset safety screen, then the valid reference frame is retained. After the current playback material is played on the electronic display screen, all the saved valid reference frames are deduplicated to obtain the number of times the valid reference frames hit the preset safe screen, and this number is used as the fourth number. The false alarm rate of the interception system is calculated using the false alarm rate calculation formula based on the third number and the fourth number.

5. The interception system performance testing method according to claim 3 or 4, characterized in that, The retention of the valid reference frame includes: Save the valid reference frame and the timestamp corresponding to the valid reference frame to obtain the set of reference frames corresponding to the currently playing material; The process of deduplicating all saved valid reference frames includes: Based on the timestamp difference and the difference threshold between different frames in the reference frame set, the reference frame set is deduplicated.

6. The interception system performance testing method according to claim 1, characterized in that, When the electronic display screen is a light-emitting diode display screen, the sampling rate of the camera is greater than or equal to the first preset sampling rate.

7. The interception system performance testing method according to claim 1, characterized in that, When the electronic display screen is a liquid crystal display screen, the sampling rate of the camera is greater than or equal to the second preset sampling rate.

8. A performance testing device for an interception system, characterized in that, include: The acquisition module is used to acquire images of the electronic display screen captured by the camera at a high-frequency sampling rate, resulting in multiple image frames of the electronic display screen corresponding to each display cycle. The electronic display screen uses an artificial intelligence interception system to automatically intercept and display a preset safe screen when it detects that the displayed screen is an illegal screen. The effective reference frame determination module is used to determine the effective reference frame corresponding to each display cycle based on the brightness and integrity of the image frame. The test result generation module is used to compare the effective reference frame with the preset security screen, and generate the performance test results of the interception system based on the comparison results and the currently playing material on the electronic display screen.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the interception system performance testing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein the computer programs, when executed by a processor, implement the interception system performance testing method as described in any one of claims 1 to 7.

Images