Evaluation method and evaluation device for contribution degree of video material, and electronic equipment

Abstract

The invention relates to the technical field of multimedia data analysis, and discloses a video material contribution degree evaluation method and device and electronic equipment. The evaluation method comprises the steps of performing shot segmentation on a finished video to determine a plurality of query fragments; based on a pre-constructed material feature library, performing feature matching on each query fragment, and determining a plurality of original video materials adopted in the finished video; determining the effective reference duration of each original video material in the finished video; and for each original video material, determining the contribution degree of the original video material in the finished video based on the effective reference duration and the total duration of the finished video. The accuracy of evaluating the contribution degree of the video material in the finished video can be improved.

Description

Technical Field

[0001] This application relates to the field of multimedia data analysis technology, such as a method and apparatus for evaluating the contribution of video material, and an electronic device. Background Technology

[0002] Currently, with the development of short video platforms, MCN agencies, and streaming media platforms, video production models have shifted from "single-person, single-film" to an "industrialized assembly line" model. In this model, photographers provide raw video footage, editors select necessary clips from a video footage library based on a creative script, and the final video is synthesized and released after multiple processes including editing, splicing, and special effects processing.

[0003] In related technologies, the contribution of video footage to the final video is usually assessed based on the number of downloads or by manual input from the editor.

[0004] In the process of implementing the embodiments of this disclosure, it was found that the related technology has at least the following problems: Downloading does not equate to using. Assessing the contribution of video footage to the final video based solely on download volume fails to distinguish whether the footage was actually used. Furthermore, manual reporting by editors carries a high risk of underreporting and misreporting. Therefore, improving the accuracy of assessing the contribution of video footage to the final video has become a pressing technical challenge.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0007] This disclosure provides a method, apparatus, and electronic device for evaluating the contribution of video footage, which can improve the accuracy of evaluating the contribution of video footage to the finished video.

[0008] In some embodiments, the method for evaluating the contribution of video footage includes: segmenting the finished video into shots to determine multiple query segments; performing feature matching on each query segment based on a pre-built feature library to determine multiple original video footage used in the finished video; determining the effective reference duration of each original video footage in the finished video; and, for each original video footage, determining the contribution of the original video footage to the finished video based on the effective reference duration and the total duration of the finished video.

[0009] Optionally, the finished video is segmented to determine multiple query segments, including: identifying shot transition points in the finished video; and dividing the finished video into multiple consecutive video segments at the shot transition points as query segments.

[0010] Optionally, based on a pre-built material feature library, feature matching is performed on each query segment to determine multiple original video materials used in the finished video, including: extracting visual content features of each query segment; and matching video materials corresponding to the visual content features in the material feature library as multiple original video materials used in the finished video.

[0011] Optionally, if there are multiple video clips in the material feature library that correspond to the visual content features, the evaluation method may further include: selecting the video clip with the highest matching similarity as the original video clip corresponding to the visual content features; or selecting the video clip with the most complete continuous duration coverage as the original video clip corresponding to the visual content features; or selecting the video clip that was added to the material feature library earliest as the original video clip corresponding to the visual content features.

[0012] Optionally, the effective reference duration of each original video clip in the finished video is determined, including: determining the time interval of each original video clip in the finished video; for each original video clip, after removing invalid time periods in the time interval, calculating the total duration of the time interval as the effective reference duration of the original video clip.

[0013] Optionally, the material feature library can be constructed by following these steps: extracting the visual content features of the original video material and constructing a unique identifier for the original video material; associating and storing the visual content features and unique identifier of the original video material to construct the material feature library; wherein, timestamp information is associated with each original video material in the material feature library.

[0014] Optionally, after determining the contribution of the original video footage to the finished video, the evaluation method may also include: obtaining market feedback data of the finished video on the publishing platform; determining the market weight and material unit price coefficient of the finished video based on the market feedback data; and calculating the product of contribution, market weight and material unit price coefficient for each original video footage as the material performance value of the original video footage in the finished video.

[0015] In some embodiments, an apparatus for evaluating the contribution of video footage includes: a segmentation module for segmenting the finished video into multiple query segments; a matching module for performing feature matching on each query segment based on a pre-built feature library to determine multiple original video footage used in the finished video; a determination module for determining the effective usage duration of each original video footage in the finished video; and a calculation module for determining the contribution of each original video footage to the finished video based on the effective usage duration of the original video footage and the total duration of the finished video.

[0016] In some embodiments, an apparatus for evaluating the contribution of video material includes a processor and a memory storing program instructions, the processor being configured to execute the evaluation method for the contribution of video material as described above when the program instructions are executed.

[0017] In some embodiments, the electronic device includes: a device body; and the aforementioned assessment device for video material contribution, which is mounted on the device body.

[0018] The method, apparatus, and electronic device for evaluating the contribution of video materials provided in this disclosure can achieve the following technical effects: In this embodiment, when evaluating the contribution of video footage to the finished video, the finished video is first divided into multiple query segments using shot segmentation. Then, each query segment is matched against a pre-built feature library to determine the multiple original video clips used in the finished video. This improves the accuracy of identifying multiple original video clips compared to matching video footage based on the entire finished video. After identifying the multiple original video clips used in the finished video, for each original video clip, its effective usage duration in the finished video is first determined. Then, based on the effective usage duration and the total duration of the finished video, the contribution of the original video clip to the finished video is calculated. This replaces subjective human judgment with objective data, making the evaluation results more closely reflect the actual contribution of the original video clips to the finished video, compared to the editor's subjective reporting of contribution. Therefore, this embodiment can improve the accuracy of evaluating the contribution of video footage to the finished video.

[0019] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0020] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein: Figure 1 This is a schematic diagram of an electronic device provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of a method for evaluating the contribution of video material provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of another method for evaluating the contribution of video material provided in this disclosure embodiment; Figure 4 This is a schematic diagram of another method for evaluating the contribution of video material provided in this disclosure embodiment; Figure 5 This is a schematic diagram of an evaluation device for the contribution of video material provided in an embodiment of this disclosure; Figure 6 This is a schematic diagram of an apparatus for evaluating the contribution of video material provided in an embodiment of this disclosure. Detailed Implementation

[0021] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0022] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0023] Unless otherwise stated, the term "multiple" means two or more.

[0024] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0025] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0026] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0027] It should be noted that, unless otherwise specified, the embodiments and features described in the present disclosure can be combined with each other.

[0028] like Figure 1 As shown, the electronic device 100 provided in this embodiment includes a device body 110 and an evaluation device 500 (600) for the contribution of video material.

[0029] Specifically, an evaluation device 500 (600) for assessing the contribution of video material is provided on the device body 110.

[0030] Optionally, the evaluation device 600 for the contribution of video footage includes a processor. When evaluating the contribution of video footage to the finished video, the processor can segment the finished video into multiple query segments and perform feature matching between each query segment and a pre-built feature library to determine multiple original video clips used in the finished video. After determining the multiple original video clips used in the finished video, for each original video clip, the processor can determine the effective usage duration of the original video clip in the finished video, and based on the effective usage duration and the total duration of the finished video, determine the contribution of the original video clip to the finished video.

[0031] In conjunction with the aforementioned electronic devices, this disclosure provides a method for evaluating the contribution of video footage, wherein the execution entity of this evaluation method can be the processor of a device for evaluating the contribution of video footage. For example... Figure 2 As shown, the evaluation method includes: S201, the processor performs shot segmentation on the finished video to determine multiple query segments.

[0032] Specifically, a shot is the basic unit of a video. Different shots contain different scenes, actions, or content. By segmenting the finished video into multiple query segments (a query segment is a video clip), the query segments can be used as the basic unit for subsequent matching with the material feature library, which is conducive to more accurately locating the original video material used in the finished video.

[0033] Optionally, shot segmentation can be performed using features such as color, texture, and shape of the image. For example, the color histogram difference between adjacent frames in the finished video can be calculated, and if the difference exceeds a certain threshold, the two frames are considered to belong to different shots. Another example is using edge detection algorithms to extract image edge information, and determining shot boundaries by comparing changes in edge features between adjacent frames in the finished video.

[0034] Optionally, shot segmentation can be performed by analyzing the motion of objects in the finished video. For example, motion vectors of pixels between adjacent frames in the finished video can be calculated using optical flow. When the motion vectors change significantly, the two frames are considered to belong to different shots.

[0035] Optionally, shot segmentation can be performed by combining audio information from the finished video. For example, shot segmentation can be performed based on characteristics such as audio volume, pitch, and timbre.

[0036] S202, the processor performs feature matching on each query segment based on a pre-built material feature library to determine the multiple original video materials used in the finished video.

[0037] Specifically, the material feature library is a pre-built database that stores the visual content features and unique identifiers of the original video materials.

[0038] Specifically, a similarity measurement method can be used to calculate the similarity between the video content features of the query segment and the video content features of each video material in the material feature library. Based on the similarity, the video material corresponding to the query segment can be determined, and then these video materials can be identified as multiple original video materials used in the finished video.

[0039] Optionally, the similarity measurement method includes at least one of cosine similarity, Euclidean distance, and Manhattan distance.

[0040] Optionally, the material feature library can be constructed by following these steps: extracting the visual content features of the original video material and constructing a unique identifier for the original video material; associating and storing the visual content features and unique identifier of the original video material to construct the material feature library; wherein, timestamp information is associated with each original video material in the material feature library.

[0041] S203, the processor determines the effective usage duration of each original video clip in the finished video.

[0042] Specifically, effective usage time measures the actual amount of time original video footage is used in the finished video, reflecting its importance and frequency of use. It is a crucial indicator for calculating the contribution of original video footage to the finished video. Therefore, it is necessary to determine the effective usage time of each piece of original video footage in the finished video.

[0043] Specifically, the effective usage duration of the original video footage can be calculated by determining the start and end times of its appearance in the finished video.

[0044] S204, the processor determines the contribution of each original video clip to the finished video based on the effective usage duration and the total duration of the finished video.

[0045] Optionally, the ratio of effective citation time to the total duration of the finished video can be calculated as the contribution of the original video material to the finished video.

[0046] Specifically, by calculating the ratio of effective citation time to the total duration of the finished video, the usage of original video footage in the finished video can be quantified into a value between 0 and 1. This value directly reflects the contribution of the original video footage to the finished video. A larger ratio indicates that the original video footage is more important and used more frequently in the finished video. Therefore, the ratio of effective citation time to the total duration of the finished video can be calculated as the contribution of the original video footage to the finished video.

[0047] Optionally, since different video materials have different roles and importance in the finished video, the criticality of the original video materials in the finished video can be determined first. After calculating the ratio of the effective reference time to the total duration of the finished video, the product of the ratio and the weight coefficient corresponding to the criticality is used as the final contribution.

[0048] Optionally, the criticality of the original video footage in the final video can be assessed based on the type of the original video footage (e.g., main character shot, background shot, etc.) and the position of the original video footage in the video (e.g., climax).

[0049] In this embodiment, when evaluating the contribution of video footage to the finished video, the finished video is first divided into multiple query segments using shot segmentation. Then, each query segment is matched against a pre-built feature library to determine the multiple original video clips used in the finished video. This improves the accuracy of identifying multiple original video clips compared to matching video footage based on the entire finished video. After identifying the multiple original video clips used in the finished video, for each original video clip, its effective usage duration in the finished video is first determined. Then, based on the effective usage duration and the total duration of the finished video, the contribution of the original video clip to the finished video is calculated. This replaces subjective human judgment with objective data, making the evaluation results more closely reflect the actual contribution of the original video clips to the finished video, compared to the editor's subjective reporting of contribution. Therefore, this embodiment can improve the accuracy of evaluating the contribution of video footage to the finished video.

[0050] In some embodiments, segmenting the finished video to determine multiple query segments includes: identifying shot transition points in the finished video; and dividing the finished video into multiple consecutive video segments at the shot transition points as query segments.

[0051] Specifically, a shot is the basic unit of a finished video, and different shots contain different scenes, actions, objects, or narrative content. Shot transition points are the dividing points between these scenes, actions, objects, or narrative content. Therefore, it is necessary to identify shot transition points in the finished video.

[0052] Optionally, transition points in the finished video can be identified based on differences in image features, motion features, or audio features between adjacent frames. For example, the color histogram difference between adjacent frames can be calculated, and if the color histogram difference exceeds a set threshold, the time point between the adjacent frames is identified as a transition point. As another example, the motion vectors of pixels between adjacent frames can be calculated to determine the optical flow field, and then based on the optical flow field, it can be determined whether a sudden change in motion scene has occurred between adjacent frames. If a sudden change exists, the time point between the adjacent frames is identified as a transition point.

[0053] Optionally, camera transition points include: shear points, gradient points, and fade-in / fade-out points; Specifically, based on the identified shot transition points, the time positions that need to be cut in the finished video can be determined. By dividing the video at the time positions that need to be cut, multiple query segments can be obtained.

[0054] In this embodiment, when segmenting the finished video, the transition points in the finished video are first identified, and then the finished video is segmented based on these transition points. This helps to improve the accuracy of the multiple query segments segmented.

[0055] In some embodiments, segmenting the finished video to determine multiple query segments includes: performing speech recognition on the finished video; obtaining each text in the speech recognition result, as well as the start timestamp and end timestamp of each text in the timeline of the finished video; merging multiple adjacent texts with contextual relationships to obtain multiple merged texts; and splitting the finished video according to the start timestamp of the first text and the end timestamp of the last text in each merged text to obtain multiple query segments.

[0056] In this embodiment, by obtaining the text and its corresponding timestamp from the speech recognition results and merging the text with contextual relationships, the finished video can be accurately segmented based on the timestamp range of the merged text, ensuring the semantic integrity and coherence of each query segment and avoiding semantic breaks caused by simple time segmentation.

[0057] In some embodiments, based on a pre-built material feature library, feature matching is performed on each query segment to determine multiple original video materials used in the finished video, including: extracting visual content features of each query segment; and matching video materials corresponding to the visual content features in the material feature library as multiple original video materials used in the finished video.

[0058] Specifically, the visual content features of the query fragment include: deep learning semantic features, key point features, or hash fingerprints of the query fragment.

[0059] Specifically, a pre-trained neural network model, such as VGG or ResNet, can be used. By inputting the query fragment into the CNN model, feature vectors from the intermediate or fully connected layers of the model can be extracted as the visual content features of the query fragment.

[0060] Specifically, for each query segment, video clips with visual content features that have a similarity to the query segment exceeding a set similarity threshold can be found in the material feature library and used as the original video clips for matching. This allows the identification of multiple original video clips used in the final video.

[0061] Optionally, if there are multiple video clips in the material feature library that correspond to the visual content features, the evaluation method may further include: selecting the video clip with the highest matching similarity as the original video clip corresponding to the visual content features; or selecting the video clip with the most complete continuous duration coverage as the original video clip corresponding to the visual content features; or selecting the video clip that was added to the material feature library earliest as the original video clip corresponding to the visual content features.

[0062] It should be noted that if a query segment cannot be matched with video material in the material feature library, then it is considered that the query segment did not use video material in the material feature library.

[0063] Optionally, since the query segment may be obtained by speeding up the original video footage, a set of speed ratios can be preset during matching; the video content features of the query segment are extracted according to the speed ratio set and matched with the material feature library.

[0064] In this embodiment, when determining the multiple original video clips used in the final video, the visual content features of each query segment are first extracted, and then video clips corresponding to the visual content features are matched in the clip feature library as the multiple original video clips used in the final video. This helps to improve the accuracy of the determined original video clips.

[0065] This disclosure provides another method for evaluating the contribution of video footage, such as... Figure 3 As shown, the evaluation method includes: S301, the processor performs shot segmentation on the finished video to determine multiple query segments.

[0066] S302, the processor performs feature matching on each query segment based on a pre-built material feature library, and determines the multiple original video materials used in the finished video.

[0067] S303, the processor determines the time interval of each original video clip in the finished video.

[0068] Specifically, the time interval of the original video footage in the finished video can be determined by identifying the start and end times of its application in the finished video.

[0069] S304: For each original video clip, the processor removes invalid time periods from the time interval and calculates the total duration of the time interval as the valid reference duration of the original video clip.

[0070] Specifically, invalid time periods refer to the time intervals within the original video footage in the finished video where invalid frames such as the opening credits, closing credits, or black screens are used.

[0071] Specifically, after removing invalid time periods from the time interval, the total duration of the time interval is calculated as the effective reference duration of the original video material, which can improve the accuracy of the determined effective reference duration of the original video material.

[0072] S305: For each original video clip, the processor determines its contribution to the finished video based on the effective usage duration and the total duration of the finished video.

[0073] In this embodiment, to determine the effective usage duration of the original video footage in the finished video, invalid time periods within the time interval are first removed, and then the total duration of the time interval is calculated as the effective usage duration of the original video footage. This improves the accuracy of the determined effective usage duration of the original video footage, thereby improving the accuracy of the determined contribution of the original video footage to the finished video.

[0074] This disclosure provides another method for evaluating the contribution of video footage, such as... Figure 4 As shown, the evaluation method includes: S401, the processor performs shot segmentation on the finished video to determine multiple query segments.

[0075] S402, the processor performs feature matching on each query segment based on a pre-built material feature library, and determines the multiple original video materials used in the finished video.

[0076] S403, the processor determines the effective usage duration of each original video clip in the finished video.

[0077] S404: For each original video clip, the processor determines the contribution of the original video clip to the finished video based on the effective reference duration and the total duration of the finished video.

[0078] The S405 processor acquires market feedback data for the finished video on the publishing platform.

[0079] Specifically, market feedback data related to the finished video can be obtained through the platform where the finished video is published.

[0080] Optionally, market feedback data includes: views, likes, comments, shares, favorites, and completion rate of the finished video.

[0081] The S406 processor determines the market weight and material unit price coefficient of the finished video based on market feedback data.

[0082] Specifically, each indicator in the market feedback data is assigned a corresponding weight value, and the sum of the weight values ​​of each indicator is 1. For example, the weight of play count is 0.4, the weight of like count is 0.2, the weight of comment count is 0.1, the weight of share count is 0.2, and the weight of favorite count is 0.1.

[0083] Specifically, after obtaining market feedback data for the finished video on the publishing platform, the market weight of the finished video can be calculated based on the weight values ​​of each indicator. For example, if a finished video has 10,000 views, 2,000 likes, 500 comments, 3,000 shares, and 1,000 favorites, its market weight calculated according to the above weight values ​​is: 10,000 × 0.4 + 2,000 × 0.2 + 500 × 0.1 + 3,000 × 0.2 + 1,000 × 0.1 = 4,000 + 400 + 50 + 600 + 100 = 5150. Normalizing this value will then determine the market weight.

[0084] Specifically, the revenue tier of the finished video can be determined based on market feedback data, and different revenue tiers correspond to different material unit price coefficients. Therefore, the material unit price coefficient of the finished video can be determined based on market feedback data.

[0085] The S407 processor calculates the product of contribution, market weight, and unit price coefficient for each original video clip, which serves as the clip performance value in the finished video.

[0086] Specifically, after determining the market weight and unit price coefficient of each original video clip in the final video, the contribution, market weight, and unit price coefficient are multiplied together to obtain the clip's performance value in the final video. For example, if an original video clip has a contribution of 0.2, a market weight of 0.5, and a unit price coefficient of 1.2, its performance value can be calculated as: 0.2 × 0.5 × 1.2 = 0.12.

[0087] In this embodiment, after calculating the contribution of the original video footage to the finished video, market feedback data of the finished video on the publishing platform is also obtained to determine the market weight and unit price coefficient of the finished video. Then, for each original video footage, the product of the contribution, market weight, and unit price coefficient is calculated as the footage performance value of the original video footage in the finished video. This facilitates the subsequent provision of corresponding performance based on the footage performance value to the provider of the original video footage.

[0088] Combination Figure 5As shown in the figure, this disclosure provides an evaluation device 500 for the contribution of video footage, including: a segmentation module 501, a matching module 502, a determination module 503, and a calculation module 504. The segmentation module 501 is used to segment the finished video into multiple query segments. The matching module 502 is used to perform feature matching on each query segment based on a pre-built feature library to determine multiple original video clips used in the finished video. The determination module 503 is used to determine the effective usage duration of each original video clip in the finished video. The calculation module 504 is used to determine the contribution of each original video clip in the finished video based on the effective usage duration of the original video clip and the total duration of the finished video.

[0089] Combination Figure 6 As shown, this disclosure provides an apparatus 600 for evaluating the contribution of video footage, comprising a processor 601 and a memory 602. Optionally, the apparatus may further include a communication interface 603 and a bus 604. The processor 601, communication interface 603, and memory 602 can communicate with each other via the bus 604. The communication interface 603 can be used for information transmission. The processor 601 can invoke logical instructions stored in the memory 602 to execute the video footage contribution evaluation method described in the above embodiments.

[0090] Furthermore, the logic instructions in the aforementioned memory 602 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0091] The memory 602, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 601 executes functional applications and data processing by running the program instructions / modules stored in the memory 602, that is, it implements the method for evaluating the contribution of video materials in the above embodiments.

[0092] The memory 602 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 602 may include high-speed random access memory and may also include non-volatile memory.

[0093] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the above-described evaluation method for the contribution of video material.

[0094] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., and other media capable of storing program code.

[0095] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0096] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0097] The methods and products disclosed in the embodiments herein (including but not limited to devices and equipment) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to implement this embodiment according to actual needs. In addition, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0098] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for evaluating the contribution of video material, characterized in that, include: Segment the finished video to identify multiple query segments; Based on a pre-built material feature library, feature matching is performed on each query segment to determine multiple original video materials used in the finished video; Determine the effective usage duration of each original video clip in the finished video; For each original video clip, the contribution of the original video clip to the finished video is determined based on the effective usage time and the total duration of the finished video.

2. The evaluation method according to claim 1, characterized in that, The finished video is segmented to determine multiple query segments, including: Identify shot transition points in the finished video; At the camera transition points, the finished video is divided into multiple consecutive video segments, which are then used as query segments.

3. The evaluation method according to claim 1, characterized in that, Based on a pre-built feature library, feature matching is performed on each query segment to determine multiple original video clips used in the final video, including: Extract the visual content features of each query segment; Video clips that match the visual content features in the material feature library are used as multiple original video clips in the finished video.

4. The evaluation method according to claim 3, characterized in that, When multiple video clips matching the visual content features in the material feature library are found, the evaluation method also includes: Select the video footage with the highest matching similarity as the original video footage corresponding to the visual content features; or... Select the video footage with the most complete continuous duration coverage as the original video footage corresponding to the visual content features; or... The video footage that was added to the feature library earliest was selected as the original video footage corresponding to the visual content features.

5. The evaluation method according to claim 1, characterized in that, Determine the effective usage duration of each original video clip in the finished video, including: Determine the time interval for each original video clip in the finished video; For each original video clip, after removing invalid time periods from the time interval, the total duration of the time interval is calculated as the valid reference duration of the original video clip.

6. The evaluation method according to any one of claims 1 to 5, characterized in that, Build a material feature library by following these steps: Extract the visual content features of the original video footage and construct a unique identifier for the original video footage; The visual content features and unique identifiers of the original video footage are associated and stored to build a footage feature library; the footage feature library associates timestamp information with each original video footage.

7. The evaluation method according to any one of claims 1 to 5, characterized in that, After determining the contribution of the original video footage to the final video, the evaluation methods also include: Obtain market feedback data for the finished videos on the publishing platform; Based on market feedback data, determine the market weight of the finished video and the unit price coefficient of the materials; For each original video clip, the product of contribution, market weight, and clip unit price coefficient is calculated as the clip performance value in the finished video.

8. A device for evaluating the contribution of video material, characterized in that, include: The segmentation module is used to segment the finished video into multiple query segments. The matching module is used to perform feature matching on each query segment based on a pre-built material feature library to determine the multiple original video materials used in the finished video. The determination module is used to determine the effective usage duration of each original video clip in the finished video; The calculation module is used to determine the contribution of each original video clip to the finished video based on the effective usage duration of the original video clip and the total duration of the finished video.

9. An apparatus for evaluating the contribution of video material, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to, when running the program instructions, execute the evaluation method for the contribution of video material as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Equipment body; The evaluation device for the contribution of video material as described in claim 8 or 9 is installed on the device body.

Images