Advertising video material placement effect evaluation method, device, equipment and storage medium

Abstract

The present invention relates to the field of image processing technology, and solves the problems that in the prior art, an advertisement finished video cannot be associated with original materials, and the accuracy of evaluating the placement effect of materials in different scenarios is low. The present invention provides an advertisement video material placement effect evaluation method, device, equipment and storage medium. The method includes: obtaining at least one original video material uploaded by a target object in an advertisement placement scenario; performing scene switching detection on the original video material, and splitting the original video material into multiple scene video segments; embedding preset blind watermark information into each frame image in each scene video segment based on frequency domain transformation to obtain a target video collection; extracting the blind watermark information from the target video collection to determine material segment information, and when the advertisement is placed, evaluating each material segment according to the placement data information and the material segment information to determine a placement effect evaluation result. The present invention provides accurate material performance data, which helps advertisers optimize the use of materials.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method, device, equipment and storage medium for evaluating the delivery effect of advertising video materials. Background Art

[0002] With the rapid development of the digital advertising market, the management of advertising materials and the analysis of delivery effects have become important links in the advertising industry. The existing advertising material management technologies mainly include the storage, classification and retrieval of materials, while the delivery effect analysis technologies focus on the data collection and basic analysis after advertising delivery. These technologies usually rely on infrastructure such as cloud storage services, content management systems (CMS) and advertising servers. However, the existing technologies have the following limitations: Material management usually relies on manual operations, which is prone to cause repeated use of materials, version confusion and loss, and the correlation between the finished advertising films and the original materials is not strong, resulting in the inability to accurately track the usage effects of materials; The monitoring and analysis of advertising effects mostly rely on overall data and lack detailed analysis of the performance of specific materials.

[0003] The existing Chinese patent CN104954819A discloses a method for realizing intelligent monitoring and broadcasting of new media advertisements by using digital watermark coding technology. It includes: First, classify and manage the new media advertisements to be broadcast through the advertising material management module, then perform watermark insertion processing on the new media advertisements to be broadcast by the digital watermark coding module and assign a unique coding identifier. The terminal device transmits the result parsed by the user terminal (the unique coding containing the digital watermark) back to the national advertising material library through the Internet or the two-way backhaul network of the radio and television network operator. Then, by comparing the advertising parsing data of the collected user terminals with the front-end advertising material library, obtain the advertising monitoring data such as which new media advertisement content the user has watched and the reach frequency of specific advertisements. Although the above patent discloses a technical solution for obtaining advertising monitoring data by comparing advertising parsing data with the material library, the correlation between the finished advertising film and the original material is not strong. Once the material is used in multiple finished films or delivered on different platforms, it is difficult to track its specific performance and contribution, which limits the improvement and optimization of material utilization rate; And there is a lack of detailed analysis of the performance of specific materials, which leads to the inability to accurately evaluate the effects of materials in different scenarios, thus making it difficult to implement targeted optimization strategies.

[0004] Therefore, how to associate the finished advertising film with the original material and accurately evaluate the delivery effects of the material in different scenarios is an urgent problem to be solved. Summary of the Invention

[0005] In view of this, the present invention provides an evaluation method, device, equipment and storage medium for the advertising video material placement effect, so as to solve the problem in the prior art that the advertising finished film cannot be associated with the original material, and the accuracy of evaluating the placement effect of the material in different scenarios is low.

[0006] The technical solution adopted by the present invention is:

[0007] In the first aspect, the present invention provides an evaluation method for the advertising video material placement effect, and the method includes:

[0008] S1: Obtain at least one original video material uploaded by the target object in the advertising placement scenario;

[0009] S2: Perform scene switching detection on the original video material, and according to the scene switching detection result, split the original video material into multiple scene video segments;

[0010] S3: Use the image processing technology based on frequency domain transformation to embed the preset blind watermark information into each frame image in each scene video segment, and perform editing on each scene video segment after embedding the blind watermark information to obtain the target video collection;

[0011] S4: Extract the blind watermark information from the target video collection, and determine the material segment information according to the extracted blind watermark information, wherein the material segment information at least includes the name and position of the original video material used in the target video collection;

[0012] S5: When the target video collection is used for advertising placement, evaluate each material segment according to the pre-collected placement data information and the material segment information, and summarize all material evaluation results to obtain the placement effect evaluation result.

[0013] Preferably, the S2 includes:

[0014] S21: Decompose the original video material into multiple frames of original video images, and obtain the color histogram corresponding to each original video image;

[0015] S22: Calculate the difference between the color histograms of adjacent frames of original video images to obtain the color histogram variance value;

[0016] S23: If the color histogram variance value is greater than the preset color histogram threshold, classify the adjacent frames of original video images into two scene video segments.

[0017] Preferably, the preset color histogram threshold is determined through the following steps:

[0018] S2301: Obtain the current frame image in the adjacent frames of original video images;

[0019] S2302: Determine the color histogram set of all frame images before the current frame image based on the current frame image;

[0020] S2303: Determine the color histogram threshold based on the color histogram set, in combination with a preset smoothing parameter and an initial threshold.

[0021] Preferably, the S3 includes:

[0022] S31: Perform color space conversion on each frame image in each scene video segment to obtain a target color channel;

[0023] S32: Perform discrete cosine transform on the target color channel to convert each frame image in each scene video segment into a scene frequency domain image;

[0024] S33: Modify the high-frequency region in the scene frequency domain image according to a preset secret key, and embed the preset blind watermark information into the scene frequency domain image.

[0025] Preferably, the S33 includes:

[0026] S331: Obtain the template size of the area to be embedded according to the preset blind watermark information;

[0027] S332: Select any target area in the scene frequency domain image according to the template size of the area to be embedded, where the size of the target area is the same as the template size of the area to be embedded;

[0028] S333: Analyze the frequency domain coefficients of the target area, and calculate the sum of the squares of all frequency domain coefficients in the target area as the area energy value;

[0029] S334: Compare the area energy value with a preset energy threshold. If the area energy value is greater than the energy threshold, classify the target area as a high-frequency area;

[0030] S335: If the area energy value is less than or equal to the energy threshold, classify the target area as a low-frequency area;

[0031] S336: Repeat steps S332 to S335 until all areas in the scene frequency domain image are classified as high-frequency areas or low-frequency areas;

[0032] S337: Obtain multiple frames of scene frequency domain images, and select one scene frequency domain image as the current frame image;

[0033] S338: Use the optical flow method to analyze the positions of each pixel point in the high-frequency area of the current frame image and the positions of each pixel point in the previous frame image, and determine the optical flow field corresponding to each pixel point;

[0034] S339: Calculate the mean value of the optical flow field corresponding to each pixel point to determine the optical flow mean value corresponding to the high-frequency region in the current frame image;

[0035] S3310: When the optical flow mean value is less than a preset optical flow threshold, perform modification processing on the high-frequency region in the current frame image, and embed the preset blind watermark information into the scene frequency-domain image;

[0036] S3311: Repeat steps S337 to S3310 until the preset blind watermark information is embedded into all scene frequency-domain images.

[0037] Preferably, the S5 includes:

[0038] S51: According to the material segment information, perform second-level statistics on the pre-collected delivery data to determine real-time evaluation parameters related to the evaluation of the original video material and the number of times the original video material is used in the advertisement delivery, where the real-time evaluation parameters at least include: real-time material play count, real-time material click-through rate, and real-time material dropout rate;

[0039] S52: According to the number of times of use, if the original video material is used once, determine the single-material evaluation result according to the evaluation parameters and the position of the original video material;

[0040] S53: If the original video material is used multiple times, perform weighted average calculation on the single-material evaluation results corresponding to each time of the original video material according to the real-time material play count to determine the multi-material evaluation result.

[0041] Preferably, the S52 includes:

[0042] S521: Obtain the total duration of the target video collection, and determine the material position gear according to the position of the original video material and the total duration;

[0043] S522: Determine the standard parameters according to the material position gear, where the standard parameters at least include standard material play count, standard material click-through rate, and standard material dropout rate;

[0044] S523: Calculate the standard parameters and the evaluation parameters to determine the single-material evaluation result.

[0045] In a second aspect, the present invention provides an advertisement video material delivery effect evaluation device, and the device includes:

[0046] An original video material acquisition module, configured to acquire at least one original video material uploaded by a target object in an advertisement delivery scenario;

[0047] A scene switching detection module is used to detect scene switching of the original video material, and according to the scene switching detection result, the original video material is segmented into multiple scene video segments;

[0048] A blind watermark embedding module is used to use image processing technology based on frequency domain transformation to embed preset blind watermark information into each frame image of each scene video segment, and clip each scene video segment after embedding the blind watermark information to obtain a target video collection;

[0049] A blind watermark extraction module is used to extract blind watermark information from the target video collection, and according to the extracted blind watermark information, determine material segment information, where the material segment information at least includes the name and location of the original video material used in the target video collection;

[0050] A material evaluation module is used to evaluate each material segment according to pre-collected placement data information and the material segment information when the target video collection is used for advertising placement, and summarize all material evaluation results to obtain a placement effect evaluation result.

[0051] In a third aspect, an embodiment of the present invention further provides an electronic device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, and when the computer program instructions are executed by the processor, the method in the first aspect of the above implementation manner is implemented.

[0052] In a fourth aspect, an embodiment of the present invention further provides a storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by the processor, the method in the first aspect of the above implementation manner is implemented.

[0053] In summary, the beneficial effects of the present invention are as follows:

[0054] The method, device, equipment and storage medium for evaluating the delivery effect of advertising video materials provided by the present invention, the method includes: obtaining at least one original video material uploaded by a target object in an advertising delivery scenario; performing scene change detection on the original video material, and splitting the original video material into multiple scene video segments; using an image processing technology based on frequency domain transformation to embed preset blind watermark information into each frame image in each scene video segment, and editing the scene video segments after embedding the blind watermark information to obtain a target video collection; extracting the blind watermark information from the target video collection, and determining material segment information according to the extracted blind watermark information, wherein the material segment information at least includes the name and position of the original video material used in the target video collection; when the target video collection is used for advertising delivery, evaluating each material segment according to the pre-collected delivery data information and the material segment information, and summarizing all material evaluation results to obtain a delivery effect evaluation result. By performing scene change detection on the original video material, splitting the original video material into multiple scene video segments, and using an image processing technology based on frequency domain transformation to embed blind watermark information into each frame image of each scene segment, the present invention ensures that each material segment can be uniquely identified. In the edited target video collection, by extracting the blind watermark information, the position and usage of each original video material can be accurately identified and traced. When advertising is delivered, according to the pre-collected delivery data information and the extracted material segment information, the delivery effect of each original video material can be accurately evaluated. It not only solves the problem of weak correlation between the advertising finished film and the original video material, but also can provide accurate material performance data through refined evaluation, which helps advertisers optimize the use of materials and improve the efficiency and effect of advertising delivery. This systematic and automated processing and analysis process reduces manual intervention and subjective deviation, and improves the accuracy and real-time performance of the evaluation. Description of the Drawings

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings, and all of them are within the protection scope of the present invention.

[0056] Figure 1 It is a schematic flow chart of the overall work of the method for evaluating the delivery effect of advertising video materials in Embodiment 1 of the present invention;

[0057] Figure 2 It is a schematic flow chart of performing scene change detection on the original video material in Embodiment 1 of the present invention;

[0058] Figure 3 It is a schematic flow chart of determining the color histogram threshold in Embodiment 1 of the present invention;

[0059] Figure 4 It is a schematic flowchart for embedding the preset blind watermark information into each frame of the images in each scene video segment in Embodiment 1 of the present invention;

[0060] Figure 5 It is a schematic flowchart for extracting the blind watermark information from the target video collection edited from each scene video segment after embedding the blind watermark information in Embodiment 1 of the present invention;

[0061] Figure 6 It is a schematic flowchart for evaluating each material segment in Embodiment 1 of the present invention;

[0062] Figure 7 It is a schematic flowchart for determining the single material evaluation result in Embodiment 1 of the present invention;

[0063] Figure 8 It is a structural block diagram of an advertising video material placement effect evaluation device in Embodiment 2 of the present invention;

[0064] Figure 9 It is a schematic structural diagram of an electronic device in Embodiment 3 of the present invention. Detailed implementation manners

[0065] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or sequence between these entities or operations. In the description of the present invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, the elements defined by the statement "comprising..." do not exclude the existence of additional identical elements in the process, method, article or device comprising the said elements. If there is no conflict, the embodiments of the present invention and the various features in the embodiments may be combined with each other, and all are within the protection scope of the present invention.

[0066] Embodiment 1

[0067] Please refer to Figure 1 , Embodiment 1 of the present invention discloses an evaluation method for the placement effect of advertising video materials, and the method includes:

[0068] S1: Obtain at least one original video material uploaded by a target object in an advertising placement scenario;

[0069] Specifically, obtaining the original video material uploaded by the target object in the advertising placement scenario means first receiving the video file uploaded by the user and using it as the initial input data. The original video material contains various types of content, such as product advertisements, brand promotions, movie and TV drama clips, and user-generated content (UGC). The original video material covers different scenarios, themes, and styles, and has the characteristics of diversification and complexity. By further processing these original video materials, it lays a foundation for the subsequent identification and evaluation of material segments, so as to ensure that when the original video materials are edited and placed, the usage and placement effect of each material segment can be accurately extracted and analyzed.

[0070] S2: Perform scene change detection on the original video material, and split the original video material into multiple scene video segments according to the scene change detection results;

[0071] Specifically, performing scene change detection on the original video material means using image processing and computer vision techniques to automatically identify the transition points between different scenes in the video, such as the moment of switching from one scene to another. According to these scene change detection results, the original video material is split into multiple scene video segments, and each segment represents a continuous visual and content unit. This process can not only accurately locate the start and end positions of each scene, but also provide a clear segmentation basis for subsequent blind watermark embedding and material management, ensuring that each segment can be independently and accurately tracked and analyzed in subsequent editing, delivery, and effect evaluation. In this way, by refining the processing of video materials, each scene segment can be managed and utilized more efficiently, improving the accuracy of overall advertising delivery and the accuracy of effect evaluation.

[0072] In one embodiment, please refer to Figure 2 , S2 includes:

[0073] S21: Decompose the original video material into multiple frames of original video images, and obtain the color histograms corresponding to the original video images;

[0074] Specifically, decomposing the original video material into multiple frames of original video images is the first step in scene change detection. First, the continuous original video material is decomposed into individual original video images. Usually, a video per second contains multiple frames (such as 30 frames per second). Each frame image represents an instantaneous picture in the video. Next, calculate the color histogram for each frame of the original video image. The color histogram is a statistical chart that represents the number of pixels of each color in the image. By calculating the color histogram of each frame (denoted as H_i), the color distribution characteristics of each frame of the original video image can be obtained, and these characteristics are used in subsequent scene change detection.

[0075] S22: Calculate the difference between the color histograms of adjacent frames of original video images to obtain the color histogram variance value;

[0076] Specifically, after obtaining the color histogram of each frame of the original video image, calculate the color histogram difference between adjacent frames, which is achieved by calculating the difference between the color histograms of adjacent frames. Common methods include relative entropy (KL divergence) or L2 norm. For frames F_i and F_{i+1}, calculate their color histogram difference D_i = d(H_i, H_{i+1}), where d can be KL divergence or L2 norm. In this way, the degree of change in the color distribution of adjacent frame images is quantified. The calculation of the color histogram variance value is an important basis for detecting scene changes because scene changes are usually accompanied by significant changes in the image color.

[0077] S23: If the color histogram variance value is greater than a preset color histogram threshold, classify the adjacent frame original video images into two scene video segments.

[0078] Specifically, to determine whether there is a scene change, compare the calculated color histogram variance value D_i of each frame with the preset color histogram threshold T_i. To improve the robustness of the detection, an adaptive threshold is used, which is dynamically adjusted according to the changes of the current frame. If the color histogram variance value D_i of a certain frame is greater than the adaptive threshold T_i, it is considered that there is a scene change between frames F_i and F_{i+1}. At this time, cut the adjacent frame original video images into two different scene video segments, thereby realizing the scene cutting of the video material. This method ensures that each scene video segment has consistent visual features and is significantly different from other scenes.

[0079] In one embodiment, please refer to Figure 3 , the preset color histogram threshold is determined through the following steps:

[0080] S2301: Obtain the current frame image in the adjacent frame original video images;

[0081] Specifically, during the process of scene change detection, the original video material is processed frame by frame. First, obtain the current frame image in the adjacent frame original video images, that is, the current frame being processed. This frame image is the target of the current analysis. By calculating the color histogram difference between it and the previous frame image, it can be determined whether there is a scene change.

[0082] S2302: According to the current frame image, determine the color histogram set of all frame images before the current frame image;

[0083] Specifically, after obtaining the current frame image, collect the set of color histograms of all the frame images before the current frame image. This set contains the color histograms (H_1, H_2,..., H_{i - 1}) of each frame from the start of the video to the current frame. These histograms represent the color distributions of the respective frame images. By analyzing this data, the color changes in the previous few frames of the video can be understood. This information is very important for calculating the change trend of the current frame and subsequent threshold adjustment.

[0084] S2303: Determine the color histogram threshold based on the set of color histograms, in combination with a preset smoothing parameter and an initial threshold.

[0085] Specifically, to make the detection more robust, an adaptive threshold is used to determine whether there is a scene change. Based on the set of color histograms, in combination with a preset smoothing parameter (α) and an initial threshold (T), the threshold (T_i) of the current frame is dynamically adjusted. The specific calculation method is T_i = αT + (1 - α)M_i, where M_i is the average difference of the previous n frames, expressed as M_i = (1 / n)Σ_{j = i - n + 1}^{i}D_j. In this way, the threshold can be dynamically adjusted according to the change of the current frame, making the scene change detection more sensitive and accurate. If the color histogram difference D_i between the current frame and the previous frame is greater than this adaptive threshold T_i, the system determines that there is a scene change between these two frames. The setting of this adaptive threshold ensures flexible adjustment when processing different video materials, improving the robustness and accuracy of the detection.

[0086] In one embodiment, S23 further includes:

[0087] S231: If the color histogram variance value is greater than the preset color histogram threshold, obtain the adjacent audio frames corresponding to the adjacent frame raw video images;

[0088] Specifically, when the color histogram variance value of adjacent video frames exceeds the preset color histogram threshold, it is initially judged that there may be a scene change. At this time, in addition to relying on image information, audio information also needs to be combined for further verification. Therefore, the audio frames corresponding to these two video frames are synchronously extracted. The audio frame refers to a segment of audio data aligned with the video frame on the time axis. By obtaining these audio frames and analyzing the changes in the audio signal, it is confirmed whether a scene conversion has actually occurred. This process ensures the synchronous processing of video and audio information and lays a foundation for subsequent multimodal analysis.

[0089] S232: Use a preset audio feature extraction algorithm to perform audio analysis on the adjacent audio frames to determine the amplitude of the audio feature change between the adjacent audio frames;

[0090] Specifically, after obtaining the audio frames, analyze the adjacent audio frames, and use audio feature extraction algorithms to detect changes in the audio. The audio feature extraction algorithms include spectral analysis, pitch change detection, audio energy analysis, band energy change, and audio event detection techniques. Using the preset audio feature extraction algorithms, identify significant changes in the audio, such as the switching of background music, the start or end of a conversation, or sudden changes in ambient sound. By comparing the features of adjacent audio frames, calculate the amplitude of the audio feature change, which can reflect the intensity of the change in the audio content within a short period, thus providing an auxiliary basis for judging scene switching. If the change in the audio features is large, it means that outside the visual scene, the audio environment has also changed significantly, which further supports the judgment of scene switching.

[0091] S233: Input the original video images of adjacent frames and adjacent audio frames into a pre-trained multimodal large model, and output the text content information related to the scene;

[0092] Specifically, input the original video images of adjacent frames into a pre-trained multimodal large model for processing. The multimodal large model can comprehensively process visual and audio information and automatically generate text descriptions related to the scene or extract text information in the scene through deep learning techniques. This step includes optical character recognition (OCR) to detect and extract the text content in the video frames, such as signs, captions, or written information within the scene. In addition, the multimodal large model can also analyze the combination of the visual and audio features of the scene to generate descriptive text information, which may include explanations of the scene content, capture of semantic changes, or even transcriptions of detected conversations or important sounds. By generating or extracting this text information, it is possible to further understand the scene content at the semantic level and provide richer information for scene switching.

[0093] S234: According to the preset weights, perform weighted analysis on the audio feature change amplitude and the text content, and judge whether to split the original video images of adjacent frames into two scene video segments based on the weighted analysis result.

[0094] Specifically, after the extraction of audio and text information, according to the preset weights, weighted analysis is performed on the amplitude of audio feature changes and the text content. The purpose of the weighted analysis is to integrate multi-modal information and make a more accurate scene switching judgment. The preset weights can be adjusted according to the characteristics of the video content and the analysis objectives. For example, for music videos, the weight of audio features may be higher, while for videos with rich dialogue scenes, the weight of text content may be higher. Through this weighted analysis, audio, text, and image information are combined, and the amplitude of changes between them is comprehensively considered. If the weighted analysis result shows obvious changes, it is determined that there is a scene switch, and adjacent video frames are segmented into two different scene video clips. In this way, not only based on visual features, but also audio and text information are fully utilized to ensure the detection of scene switches is more accurate and reliable.

[0095] S3: Using image processing technology based on frequency domain transformation, embed the preset blind watermark information into each frame image in each scene video clip, and clip each scene video clip after embedding the blind watermark information to obtain the target video collection;

[0096] In one embodiment, please refer to Figure 4 , the S3 includes:

[0097] S31: Perform color space conversion on each frame image in each scene video clip to obtain the target color channels;

[0098] Specifically, convert each frame image in each scene video clip from the RGB color space to the YUV color space. The YUV color space is divided into three channels: the Y channel (luminance), the U channel (chrominance), and the V channel (concentration). The converted YUV image can more effectively separate color information from luminance information, enabling us to operate on the U and V channels without affecting the overall visual quality. Through this conversion, the target color channels (U and V) of each frame image are obtained, laying the foundation for subsequent blind watermark embedding.

[0099] S32: Perform discrete cosine transform on the target color channels to convert each frame image in each scene video clip into a scene frequency domain image;

[0100] Specifically, after obtaining the target color channels, perform discrete cosine transform (DCT) on these channels. DCT is a frequency domain transformation method that can convert an image from the spatial domain to the frequency domain. Through DCT, an image is represented as a set of frequency components, where low-frequency components contain the main image information and high-frequency components contain less detailed information. This conversion enables us to process in the frequency domain to hide blind watermark information while minimizing the impact on the visual quality of the image. After DCT processing, the U and V channels of each frame image are converted into frequency domain images, showing the weights of each frequency component.

[0101] S33: Modify the high-frequency region in the scene frequency-domain image according to a preset key, and embed the preset blind watermark information into the scene frequency-domain image.

[0102] Specifically, use the preset key to determine the specific position for embedding the blind watermark information in the frequency-domain image. The key is a parameter set for positioning, ensuring that the position of the blind watermark embedding is consistent and traceable for each frame. Select the high-frequency region in the scene frequency-domain image for modification because these regions contain less visual information, and the overall visual effect of the image is minimally affected after modification. By embedding the blind watermark information (i.e., the unique ID) in the high-frequency region, it is ensured that each frame of the image contains recognizable hidden information. This process converts the frequency-domain image back to the spatial-domain image through inverse transformation (IDCT), and finally completes the embedding of the blind watermark information. In this way, each frame of the image carries invisible identification information, ensuring that the material can be accurately identified and traced when used in the final video.

[0103] In one embodiment, S33 includes:

[0104] S331: Obtain the template size of the region to be embedded according to the preset blind watermark information;

[0105] Specifically, first, it is necessary to clarify the information content of the blind watermark, such as text, image, or other forms of data. According to the complexity and amount of information of the watermark, calculate a suitable template size for the region. For example, if the watermark is a short piece of text, a template size of 8x8 or 16x16 is sufficient, while if the watermark is an image or larger data, a larger region is required. The choice of the template size affects the clarity and visibility of the watermark. If it is too large, it will have an obvious impact on the image after embedding, and if it is too small, the information cannot be fully transmitted. Therefore, a reasonable template size can improve the concealment and transmission efficiency of the watermark.

[0106] S332: Select any target region in the scene frequency-domain image according to the template size of the region to be embedded, where the size of the target region is the same as the template size of the region to be embedded;

[0107] Specifically, select a target region in the scene frequency-domain image with the same size as the template. The selection methods include random selection or based on image features. For example, if a frequency-domain image of a static scene is selected, randomly select an 8x8 region from it. In practical applications, the selection of the target region takes into account the content characteristics of the image. For example, select a region with a relatively flat background to ensure the concealment of the watermark. If the position of the target region happens to be in a part with less texture variation, the visual effect will be better after embedding the watermark.

[0108] S333: Analyze the frequency domain coefficients of the target region, and calculate the sum of the squares of all frequency domain coefficients within the target region as the region energy value;

[0109] Specifically, analyze the frequency domain coefficients of the selected target region. By calculating the sum of the squares of all frequency domain coefficients within this region, an energy value reflecting the intensity of this region is obtained. For example, when analyzing an 8x8 DCT coefficient matrix, square each frequency domain coefficient in the matrix and then sum them up. The result obtained is the energy value of this region. This value can indicate the details and intensity of this region and is usually used to evaluate whether it is suitable for watermark embedding. For instance, if the energy value of a certain region is 50, it indicates that this region is relatively weak.

[0110] S334: Compare the region energy value with a preset energy threshold. If the region energy value is greater than the energy threshold, classify the target region as a high-frequency region;

[0111] Specifically, compare the calculated region energy value with the preset energy threshold. If the region energy value is greater than the threshold, mark it as a high-frequency region. For example, assume the preset energy threshold is 40. If the energy value of a certain target region is 45, it indicates that this region has strong details and is suitable for carrying a watermark. On the contrary, if the energy value is lower than the threshold, it is not suitable for watermark embedding. Through such classification, the system can effectively identify which regions can effectively carry watermark information without compromising the overall quality of the image.

[0112] S335: If the region energy value is less than or equal to the energy threshold, classify the target region as a low-frequency region;

[0113] Specifically, when the region energy value is less than or equal to the preset energy threshold, mark this region as a low-frequency region. Low-frequency regions usually contain fewer detailed changes and are more flat, suitable for embedding watermarks without causing obvious visual interference. For example, if the energy value is 35, it indicates that this region is relatively stable and suitable for carrying a watermark. Through such classification, a wise choice is made between high-frequency regions and low-frequency regions to ensure the visual concealment of the watermark.

[0114] S336: Repeat steps S332 to S335 until all regions in the scene frequency domain image are classified as high-frequency regions or low-frequency regions;

[0115] Specifically, a comprehensive analysis is performed on the entire scene frequency-domain image. By repeating steps S332 to S335, all target regions are evaluated one by one. The purpose of doing this is to ensure that each region is classified so that the subsequent watermark embedding strategy can be based on comprehensive data. For example, assuming there are multiple 8x8 regions in an image, each region will be analyzed one by one until all regions are marked as high-frequency or low-frequency. This process ensures that the image can be comprehensively evaluated and the most suitable regions for watermark embedding can be selected to the greatest extent.

[0116] S337: Obtain multiple frames of scene frequency-domain images, and select one scene frequency-domain image as the current frame image;

[0117] Specifically, the current frame image is obtained from multiple scene frequency-domain images. The multiple frames of images provide dynamic background information for watermark embedding, which helps to improve the robustness of the watermark. For example, in a video sequence, there may be dozens of frames of images. Selecting one frame from these frames as the current processing object can better analyze the motion of the current frame and compare it with the previous frame, facilitating the embedding of dynamic watermarks.

[0118] S338: Using the optical flow method, analyze the positions of each pixel point in the high-frequency region of the current frame image and the positions of each pixel point in the previous frame image to determine the optical flow field corresponding to each pixel point;

[0119] Specifically, the optical flow method is applied to analyze the motion in the high-frequency region of the current frame. The optical flow method can effectively extract motion information by calculating the changes in pixel positions between adjacent frames. For example, if in a video, a certain pixel point in the high-frequency region of the current frame moves 5 pixels to the left, while the pixel point at the corresponding position in the previous frame remains unchanged, this motion information will be recorded and the optical flow field will be constructed. This process provides a basis for subsequent watermark embedding, identifying which regions have less motion and are thus more suitable for watermark embedding.

[0120] S339: Calculate the mean value of the optical flow field corresponding to each pixel point to determine the optical flow mean value corresponding to the high-frequency region of the current frame image;

[0121] Specifically, calculate the mean value of all pixel points in the high-frequency region of the optical flow field to determine the overall motion state of this region. For example, if the optical flow values of multiple pixel points in the high-frequency region are 2, 3, 4, and 5 respectively, then the mean value is 3.5. This mean value can reflect the degree of motion of this region. If the mean value is small, it indicates that the motion of this region is relatively small and it is suitable for watermark embedding.

[0122] S3310: When the optical flow mean value is less than the preset optical flow threshold, perform modification processing on the high-frequency region of the current frame image, and embed the preset blind watermark information into the scene frequency-domain image;

[0123] Specifically, if the calculated average optical flow is lower than a preset optical flow threshold, the high-frequency region of the current frame will be modified to embed blind watermark information. For example, if the set optical flow threshold is 4 and the average value is 3.5, it will be determined that this region is suitable for watermark embedding. At this time, the watermark information will be added to the frequency domain coefficients of this region to ensure the concealment and effectiveness of the watermark.

[0124] S3311: Repeat steps S337 to S3310 until all the preset blind watermark information is embedded in all the scene frequency domain images.

[0125] Specifically, finally, loop through steps S337 to S3310 to process each scene frequency domain image frame by frame until all the images are completed with watermark embedding. This continuous processing method can ensure the effective transmission of watermark information in multiple frames of images and improve the robustness and concealment of the watermark. By performing dynamic analysis in each frame, it is ensured that the watermark information can maintain consistency and stability throughout the video sequence.

[0126] S4: Extract blind watermark information from the target video collection. Based on the extracted blind watermark information, determine the material segment information, where the material segment information at least includes the name and location of the original video material used in the target video collection.

[0127] Specifically, first, process each frame of the target video collection. Through the inverse discrete cosine transform (IDCT), convert the image from the frequency domain back to the spatial domain and extract the blind watermark information embedded in the high-frequency region. Using the preset key, accurately locate the specific position and content of the blind watermark information in the image. Through the extracted blind watermark information, the system can identify the unique ID in each frame of the image and thereby determine which original material segments are used in the target video collection. This process enables accurate tracking of the source and location of each material segment even if the materials are clipped, mixed, or reused in different scenes, ensuring that the references to the materials in the finished film can be perfectly identified and achieving accurate data backflow.

[0128] In one embodiment, please refer to Figure 5 , where S4 includes:

[0129] S41: Decompose the target video collection into multiple frames of target video images, perform discrete cosine transform on each of the target video images, and determine the target frequency domain images.

[0130] Specifically, the target video collection is decomposed into individual target video images, with each frame of the target video image representing an instant in the video. The discrete cosine transform (DCT) is applied to each frame of the target video image to transform the target video image from the spatial domain to the frequency domain, determining the target frequency-domain image. Through DCT, the image is decomposed into a series of frequency components, where each component represents the variation of different frequencies in the image. These determined target frequency-domain images reveal the high-frequency and low-frequency information of the image, providing a basis for the subsequent blind watermark extraction process. Through this transformation, the system can process and analyze the hidden information in the image in the frequency domain.

[0131] S42: According to the key, determine the target positions in the target frequency-domain image that contain blind watermark information;

[0132] Specifically, after obtaining the target frequency-domain image, a preset key is used to determine the specific positions of the blind watermark information in these frequency-domain images. The key is a set of predefined parameters used to identify the frequency components and positions where the blind watermark information is embedded. By referring to the key, the area in the frequency-domain image that contains the blind watermark information can be accurately found. This step ensures the accuracy of blind watermark extraction because only through the key can the embedded hidden information be correctly decoded. The use of the key enables the systematic positioning of the unique ID information hidden in each frame of the image.

[0133] S43: According to the target positions, extract and restore the blind watermark information from the target frequency-domain image to determine the material segment information.

[0134] Specifically, after determining the target positions of the blind watermark information, these positions are processed to extract the hidden blind watermark information. The extraction process includes reading the modified information in the high-frequency region from the frequency-domain image and restoring the frequency-domain information to the spatial domain through the inverse discrete cosine transform (IDCT). The extracted blind watermark information contains the embedded unique IDs, which correspond one-to-one with the original material segments. Through these IDs, it is possible to identify and confirm which original material segments are used in the target video collection, ensuring the accurate tracking of the material and the precision of data backflow. In this way, detailed usage and performance data can be provided for each material segment, thereby optimizing advertising placement and content management.

[0135] S5: When the target video collection is used for advertising placement, evaluate each material segment based on the pre-collected placement data information and the material segment information, and summarize all the material evaluation results to obtain the advertising placement effect evaluation result.

[0136] Specifically, when advertising is carried out for the target video collection, the collected advertising data is associated with and analyzed against the previously extracted material clip information. The advertising data includes key metrics such as the number of views, click-through rate, viewing duration, and user interaction. By matching this advertising data with the unique ID of each material clip, the performance of each material clip in different advertising scenarios can be accurately evaluated. During the evaluation process, various metrics are comprehensively considered, a quantitative score is given to the effect of the material clip, and a detailed evaluation report is generated. Finally, the material evaluation results are output, providing targeted optimization suggestions for advertisers to help them improve the utilization efficiency of the material and the advertising effect in future advertising creation and placement.

[0137] In one embodiment, please refer to Figure 6 , S5 includes:

[0138] S51: According to the material clip information, perform second-level statistics on the pre-collected advertising data to determine real-time evaluation parameters related to the evaluation of the original video material and the number of times the original video material is used in advertising. Among them, the real-time evaluation parameters at least include: real-time material play count, real-time material click-through rate, and real-time material dropout rate.

[0139] Specifically, according to the material clip information, the material clip information at least includes the name and location of the original video material used in the target video collection. The collected advertising data is refined and processed, and statistical analysis is carried out in seconds. Specifically, for each original video material clip, first determine its specific usage period in the video. For example, assume that the original video material clip is used between the 2nd second and the 5th second of the video. Then, the advertising data within these seconds will be focused on. For the real-time material play count, the play count at the 2nd second when the material starts to be used will be used as the evaluation benchmark. Next, calculate the average dropout rate per second of the original video material clip during its usage period. The real-time material dropout rate refers to the proportion of viewers leaving the video in a certain second. Calculate the dropout rates from the 2nd second to the 5th second respectively, and then find the average of these four values to obtain the average dropout rate per second of the material. Similarly, the click-through rate per second will also be calculated. The real-time material click-through rate reflects the interaction between the viewer and the advertisement during the video viewing process. The click-through rates from the 2nd second to the 5th second will be statistically analyzed respectively, and their average value will be calculated to obtain the average click-through rate per second of the material. Through such second-level statistics, key evaluation parameters related to material evaluation can be extracted, including play count, average dropout rate, and average click-through rate. These parameters provide basic data for subsequent material evaluation, making the evaluation process more accurate and scientific, thus helping advertisers understand the specific performance of each material in different time periods and advertising scenarios and optimize the advertising placement strategy.

[0140] S52: According to the number of times of use, if the original video material is used once, determine the single - material evaluation result based on the evaluation parameter and the position of the original video material;

[0141] Specifically, according to the number of times of use, when the original video material is used once, the single - evaluation result will be calculated using the previously collected evaluation parameter and the position of the original video material. This step ensures a detailed evaluation of each single use of the material for subsequent comprehensive evaluation.

[0142] In one embodiment, please refer to Figure 7 , S52 includes:

[0143] S521: Obtain the total duration of the target video collection, and determine the material - position gear according to the position of the original video material and the total duration;

[0144] Specifically, according to the material - segment information, determine the specific use position of the material in the target video collection, which includes the start time and end time of the material, as well as the specific time period in which it is located in the video. This step helps to understand the position where the material appears in the video and provides a reference for subsequent evaluation. According to the position of the material segment in the video and the total duration of the video, divide the material position into different gears. For example, the video can be divided into five gears: the beginning, the front, the middle, the back, and the end. Assuming the total duration of the video is 35 seconds, then each gear is approximately 7 seconds. Assume the material use position is from 12 seconds to 15.3 seconds, take the average as 13.65, calculate and round down the material center position / segment interval. According to the center position of the material segment, calculate and determine its specific gear.

[0145] S522: Determine the standard parameters according to the material - position gear, where the standard parameters at least include the standard material play count, the standard material click - through rate, and the standard material dropout rate;

[0146] Specifically, after determining the specific gear of the material, determine the standard parameters according to the material - position gear, where the standard parameters at least include the standard material play count, the standard material click - through rate, and the standard material dropout rate; and each gear corresponds to different standard parameters. For example, define reference indicators for 5 different positions respectively. R[0].ctr represents the standard click - through rate of the beginning material, and R[4].play represents the standard play count of the end material. The standard parameters provide a benchmark for subsequent evaluation, making the evaluation process more accurate and targeted.

[0147] S523: Calculate the standard parameters and the evaluation parameters to determine the single - material evaluation result. Specifically, finally, compare and analyze the evaluation parameters of the material with the standard parameters, and calculate the evaluation result of the single use of the material. The evaluation result includes the scores of various indicators. Considering the performance of the play volume, click - through rate, and dropout rate comprehensively, a comprehensive score is finally obtained. The calculation formula is:

[0148]

[0149] where ε = 0.000001, x.score represents the comprehensive score, x.play represents the number of plays of the original video material, x.ctr represents the average click - through rate per second of the original video material, x.lr represents the average dropout rate per second of the original video material, x.pos represents the position of the original video material, R[x.pos].play represents the standard number of plays at the position of the original video material, R[x.pos].ctr represents the standard click - through rate at the position of the original video material, R[x.pos].lr represents the standard dropout rate at the position of the original video material, and the symbol represents truncating the value to the lower limit a and the upper limit b. This score reflects the overall effect of the material in a single use and provides a specific evaluation basis for advertisers.

[0150] S53: If the original video material is used multiple times, based on the real - time material play count, perform a weighted average calculation on the single - material evaluation results corresponding to each time the original video material is used to determine the multiple - material evaluation result.

[0151] Specifically, in the case where the material is used multiple times, perform a weighted average calculation on the evaluation results of each use of the material. The basis for weighting is the logarithmic play count of each use, ensuring that the usage times with a large play count have a higher weight in the comprehensive evaluation. The calculation formula is as follows:

[0152]

[0153] where X[i].play represents the number of plays of the original video material corresponding to the i - th use of the original video material; X[i].score represents the single - material evaluation result corresponding to the i - th use of the original video material. In this way, a more comprehensive evaluation result can be obtained, reflecting the overall performance of the material in multiple uses. This weighted average calculation method improves the accuracy of the evaluation and helps advertisers better understand the comprehensive effect of the material in different placement scenarios.

[0154] After S5, it further includes:

[0155] S61: Obtain the advertisement type and placement platform when advertising is placed in the target video collection.

[0156] Specifically, obtain the advertising platforms and advertising types that the advertisement targets when placing advertisements in the target video collection. For example, for traditional media such as television, factors such as channel-changing time and audience viewing habits will be considered during material evaluation, while for streaming media platforms such as short-video platforms, user behavior data will be analyzed during material evaluation, such as the sending time and quantity of bullet screens, and interactive behaviors such as likes and forwards, as well as the content recommendation algorithms of the platform. In terms of advertising types, Vlog-style advertisements usually focus on the natural implantation of content and the personal style of the creator, while evaluation-style advertisements emphasize more on the performance display of the product and the trust of the audience. In this step, these data will be collected and analyzed to provide a basis for formulating subsequent advertising placement strategies, ensuring that the advertisement content and placement methods match the characteristics of the platform and advertising type, thereby improving the dissemination effect and user acceptance of the advertisement.

[0157] S62: According to the advertising type and placement platform, perform secondary correction on the material evaluation result, and use the corrected evaluation result as the placement effect analysis result.

[0158] Specifically, after obtaining the characteristics of the advertising type and placement platform, perform secondary correction on the preliminary material evaluation result. This process deeply analyzes the characteristics of the advertising type and placement platform, combines the original evaluation result with the user behavior pattern of the platform and advertising interaction data. For example, in Vlog-style advertisements, platform users tend to prefer natural and personalized content, so the score of hard advertisements will be reduced, while the score of native content advertisements will be increased; in evaluation-style advertisements, more attention will be paid to the clarity and credibility of product information to ensure the best placement effect of the advertisement on a specific platform. In addition, for streaming media platforms, key attention will be paid to user interaction behavior data such as bullet screens and likes, while in traditional media, more attention will be paid to the advertisement broadcast time period and the viewing habits of the audience. Through this series of corrections, the final evaluation result will be more accurate, which can better guide subsequent advertising placement and effect evaluation, ensuring that the advertisement achieves the expected dissemination effect.

[0159] Embodiment 2

[0160] Please refer to Figure 8 , Embodiment 2 of the present invention also provides an advertising video material placement effect evaluation device, and the device includes:

[0161] A material upload module, configured to obtain the uploaded original video material;

[0162] A material segmentation module, configured to perform scene change detection on the original video material, and according to the scene change detection result, segment the original video material into multiple scene video segments;

[0163] A blind watermark embedding module, which is used to embed preset blind watermark information into each frame of the images in each scene video segment by using image processing technology based on frequency domain transformation;

[0164] A blind watermark extraction module, which is used to extract blind watermark information from the target video collection obtained by editing each scene video segment after embedding the blind watermark information, and determine the material segment information in the target video collection according to the extracted blind watermark information;

[0165] A material evaluation module, which is used to evaluate each material segment according to the pre-collected placement data information and the material segment information when the target video collection is used for advertising placement, and output a material evaluation result.

[0166] Specifically, an advertising video material placement effect evaluation device provided by an embodiment of the present invention includes: a material upload module, which is used to obtain the uploaded original video material; a material segmentation module, which is used to perform scene change detection on the original video material, and according to the scene change detection result, segment the original video material into multiple scene video segments; a blind watermark embedding module, which is used to embed preset blind watermark information into each frame of the images in each scene video segment by using image processing technology based on frequency domain transformation; a blind watermark extraction module, which is used to extract blind watermark information from the target video collection obtained by editing each scene video segment after embedding the blind watermark information, and determine the material segment information in the target video collection according to the extracted blind watermark information; a material evaluation module, which is used to evaluate each material segment according to the pre-collected placement data information and the material segment information when the target video collection is used for advertising placement, and output a material evaluation result. This device performs scene change detection on the original video material, segments the original video material into multiple scene video segments, and embeds blind watermark information into each frame of each scene segment by using image processing technology based on frequency domain transformation to ensure that each material segment can be uniquely identified. In the edited target video collection, by extracting the blind watermark information, the position and usage of each original video material can be accurately identified and traced. When advertising is placed, according to the pre-collected placement data information and the extracted material segment information, the placement effect of each original video material can be accurately evaluated. It not only solves the problem of weak correlation between the advertising finished film and the original video material, but also can provide accurate material performance data through refined evaluation, which helps advertisers optimize the use of materials and improve the efficiency and effect of advertising placement. This systematic and automated processing and analysis process reduces manual intervention and subjective deviation, and improves the accuracy and real-time performance of the evaluation.

[0167] Embodiment 3

[0168] In addition, in combination with Figure 1The advertising video material placement effect evaluation method described in Embodiment 1 of the present invention can be implemented by an electronic device. Figure 9 FIG. shows a schematic hardware structure diagram of an electronic device provided in Embodiment 3 of the present invention.

[0169] The electronic device may include a processor and a memory storing computer program instructions.

[0170] Specifically, the above-mentioned processor may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0171] The memory may include a mass storage for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In a suitable case, the memory may include a removable or non-removable (or fixed) medium. In a suitable case, the memory may be internal or external to the data processing device. In a particular embodiment, the memory is a non-volatile solid state memory. In a particular embodiment, the memory includes a read only memory (ROM). In a suitable case, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory or a combination of two or more of these.

[0172] The processor reads and executes the computer program instructions stored in the memory to implement any one of the advertising video material placement effect evaluation methods in the above embodiments.

[0173] In one example, the electronic device may further include a communication interface and a bus. Among them, as Figure 9 shown, the processor, the memory, and the communication interface are connected by the bus and complete communication with each other.

[0174] The communication interface is mainly used to implement communication between various modules, devices, units, and / or devices in the embodiments of the present invention.

[0175] A bus includes hardware, software, or both, and couples components of the device together. By way of example and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, the bus can include one or more buses. Although embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0176] The electronic device provided in this embodiment detects scene switching of the original video material, divides the original video material into multiple scene video segments, and embeds blind watermark information into each frame image of each scene segment by using image processing technology based on frequency domain transformation to ensure that each material segment can be uniquely identified. In the edited target video collection, by extracting the blind watermark information, the position and usage of each original video material can be accurately identified and traced. When advertising is placed, based on the pre-collected placement data information and the extracted material segment information, the placement effect of each original video material can be accurately evaluated. This not only solves the problem of weak correlation between the advertising finished product and the original video material, but also can provide accurate material performance data through refined evaluation, which helps advertisers optimize the use of materials and improve the efficiency and effect of advertising placement. This systematic and automated processing and analysis process reduces manual intervention and subjective bias, and improves the accuracy and real-time performance of the evaluation.

[0177] Embodiment 4

[0178] In addition, in combination with the advertising video material placement effect evaluation method in Embodiment 1 above, Embodiment 4 of the present invention can also be implemented by providing a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the advertising video material placement effect evaluation methods in the above embodiments is implemented.

[0179] The storage medium provided in this embodiment performs scene transition detection on the original video material, divides the original video material into multiple scene video segments, and embeds the blind watermark information into each frame image of each scene segment by using the image processing technology based on frequency domain transformation to ensure that each material segment can be uniquely identified. In the edited target video collection, by extracting the blind watermark information, the position and usage of each original video material can be accurately identified and traced. When advertising is carried out, based on the pre-collected advertising placement data information and the extracted material segment information, the advertising placement effect of each original video material can be accurately evaluated. This not only solves the problem of weak correlation between the finished advertisement and the original video material, but also can provide accurate material performance data through refined evaluation, which helps advertisers optimize the use of materials and improve the efficiency and effect of advertising placement. This systematic and automated processing and analysis process reduces manual intervention and subjective deviation, and improves the accuracy and real-time performance of evaluation.

[0180] In summary, the embodiments of the present invention provide a method, device, equipment and storage medium for evaluating the advertising placement effect of video materials.

[0181] It should be clear that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, the detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications and additions, or change the order between steps after understanding the spirit of the present invention.

[0182] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties. And the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of the relevant place, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0183] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0184] As described above, this is only the specific implementation manner of the present invention. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A method for evaluating the effect of advertising video material delivery, characterized in that: The method comprises: S1: Obtain at least one original video material uploaded by the target object in the advertising delivery scenario; S2: performing scene switching detection on the original video material, and dividing the original video material into a plurality of scene video segments according to the scene switching detection result; S3: Using the image processing technology based on frequency domain transformation, the preset blind watermark information is embedded into each frame image in each scene video clip, and the video clips of each scene after the blind watermark information is embedded are edited to obtain the target video highlights; S4: extracting blind watermark information from the target video collection, and determining material segment information based on the extracted blind watermark information, wherein the material segment information at least includes the name and position of the original video material used in the target video collection; S5: when the target video collection is used for advertisement delivery, each material segment is evaluated according to the pre-collected delivery data information and the material segment information, and all material evaluation results are summarized to obtain a delivery effect evaluation result; The S5 includes: S51: performing second-level statistics on the pre-collected delivery data according to the material segment information, and determining real-time evaluation parameters related to the evaluation of the original video material and the number of times the original video material is used in the advertisement delivery, wherein the real-time evaluation parameters at least include: the number of real-time material plays, the real-time material click rate, and the real-time material loss rate; S52: according to the number of uses, if the original video material is used once, determining a single material evaluation result according to the real-time evaluation parameter and the original video material position; S53: If the original video material is used multiple times, a weighted average calculation is performed on the single material evaluation results corresponding to each original video material according to the real-time material playback number to determine multiple material evaluation results; The S52 includes: S521: Obtain the total duration of the target video collection, and determine the material position level according to the original video material position and the total duration, wherein the material position level is used to identify the relative time interval of the original video material in the target video collection; S522: determining standard parameters according to the material position, wherein the standard parameters at least include a standard material play count, a standard material click rate, and a standard material loss rate; S523: Calculate the standard parameter and the evaluation parameter to determine the single material evaluation result.

2. The method for evaluating the effect of advertising video material delivery according to claim 1, characterized in that: The S2 includes: S21: Decomposing the original video material into multiple frames of original video images, and obtaining a color histogram corresponding to each original video image; S22: performing difference calculation on the color histograms of the original video images of adjacent frames to obtain a color histogram difference value; S23: If the color histogram difference value is greater than a preset color histogram threshold, the adjacent frames of original video images are classified into two scene video segments.

3. The method for evaluating the effect of placing advertising video materials according to claim 2, characterized in that: The preset color histogram threshold is determined by the following steps: S2301: Acquire a current frame image from adjacent frames of original video images; S2302: Determine a color histogram set of all frame images before the current frame image according to the current frame image; S2303: Determine the color histogram threshold according to the color histogram set in combination with a preset smoothing parameter and an initial threshold.

4. The method for evaluating the effect of advertising video material delivery according to claim 1, characterized in that: The S3 includes: S31: performing color space conversion on each frame image in each scene video clip to obtain a target color channel; S32: performing discrete cosine transform on the target color channel to convert each frame image in each scene video clip into a scene frequency domain image; S33: modifying the high-frequency region in the scene frequency domain image according to the preset key, and embedding the preset blind watermark information into the scene frequency domain image.

5. The method for evaluating the effect of placing advertising video materials according to claim 4, characterized in that: The S33 includes: S331: Obtain the size of the template of the area to be embedded according to the preset blind watermark information; S332: selecting any target area in the scene frequency domain image according to the size of the template of the area to be embedded, wherein the size of the target area is the same as the size of the template of the area to be embedded; S333: Perform frequency domain coefficient analysis on the target area, and calculate the square sum of all frequency domain coefficients in the target area as the regional energy value; S334: comparing the regional energy value with a preset energy threshold, and if the regional energy value is greater than the energy threshold, classifying the target region as a high-frequency region; S335: If the regional energy value is less than or equal to the energy threshold, classify the target region as a low-frequency region; S336: repeating steps S332 to S335 until all regions in the scene frequency domain image are classified as high-frequency regions or low-frequency regions; S337: Acquire multiple frames of scene frequency domain images, and select a scene frequency domain image as a current frame image; S338: Using the optical flow method, analyze the position of each pixel point in the high-frequency area of ​​the current frame image and the position of each pixel point in the previous frame image to determine the optical flow field corresponding to each pixel point; S339: Calculate the mean of the optical flow field corresponding to each pixel point to determine the mean of the optical flow corresponding to the high-frequency area in the current frame image; S3310: When the optical flow mean is less than a preset optical flow threshold, modify the high-frequency area in the current frame image and embed the preset blind watermark information into the scene frequency domain image; S3311: Repeat steps S337 to S3310 until the preset blind watermark information is embedded into all scene frequency domain images.

6. An advertising video material delivery effect evaluation device, characterized in that: The device comprises: The original video material acquisition module is used to acquire at least one original video material uploaded by the target object in the advertisement delivery scenario; A scene switching detection module, used to perform scene switching detection on the original video material, and divide the original video material into a plurality of scene video segments according to the scene switching detection result; The blind watermark embedding module is used to embed the preset blind watermark information into each frame image in each scene video clip by using the image processing technology based on frequency domain transformation, and edit the scene video clips after the blind watermark information is embedded to obtain the target video highlights; A blind watermark extraction module is used to extract blind watermark information from a target video collection, and determine material segment information based on the extracted blind watermark information, wherein the material segment information at least includes the name and position of the original video material used in the target video collection; A material evaluation module is used to evaluate each material segment according to the pre-collected delivery data information and the material segment information when the target video collection is delivered for advertising, and to summarize all material evaluation results to obtain a delivery effect evaluation result; When the target video collection is used for advertising delivery, each material segment is evaluated based on the pre-collected delivery data information and the material segment information, and the delivery effect evaluation result is obtained by summarizing all material evaluation results, including: According to the material segment information, the pre-collected delivery data is counted at the second level to determine the real-time evaluation parameters related to the evaluation of the original video material and the number of times the original video material is used in the advertisement delivery, wherein the real-time evaluation parameters at least include: the number of real-time material plays, the real-time material click rate and the real-time material loss rate; According to the number of uses, if the original video material is used once, determining a single material evaluation result according to the real-time evaluation parameter and the original video material position; If the original video material is used multiple times, a weighted average calculation is performed on the single material evaluation results corresponding to each original video material according to the number of real-time material playbacks to determine multiple material evaluation results; According to the number of times of use, if the original video material is used once, determining the single material evaluation result according to the evaluation parameter and the original video material position includes: Obtain the total duration of the target video collection, and determine the material position level according to the original video material position and the total duration, wherein the material position level is used to identify the relative time interval of the original video material in the target video collection; Determining standard parameters according to the material position, wherein the standard parameters at least include the number of standard material plays, the standard material click rate, and the standard material loss rate; The standard parameter and the evaluation parameter are calculated to determine the single material evaluation result.

7. An electronic device, characterized in that: include: At least one processor, at least one memory and computer program instructions stored in the memory, when the computer program instructions are executed by the processor, implement the method according to any one of claims 1 to 5.

8. A storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images