CN109922379B - Advertisement video optimization method, device and equipment and computer readable storage medium - Google Patents
Advertisement video optimization method, device and equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109922379B CN109922379B CN201910140441.4A CN201910140441A CN109922379B CN 109922379 B CN109922379 B CN 109922379B CN 201910140441 A CN201910140441 A CN 201910140441A CN 109922379 B CN109922379 B CN 109922379B
- Authority
- CN
- China
- Prior art keywords
- video frame
- key
- advertisement
- video
- candidate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
- H04N21/8405—Generation or processing of descriptive data, e.g. content descriptors represented by keywords
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
Abstract
The invention discloses an advertisement video optimization method, device, equipment and a computer readable storage medium, wherein the method comprises the following steps: dividing an advertisement video to be optimized into a plurality of advertisement video segments, and extracting a key video frame of each advertisement video segment through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames; obtaining a key index evaluation algorithm, and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame; selecting a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame; and acquiring a key video frame preposition strategy, and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain the target advertisement video. The invention can quickly and accurately optimize the advertisement video.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for advertisement video optimization.
Background
Along with financial technology (Fintech), especially the rapid development of internet finance, more and more enterprises adopt online mode to promote brand and product gradually, can put in the advertisement video that is used for promoting brand and product through each big advertisement platform, can let more people watch the advertisement video, and the everybody of being convenient for knows brand and product, can be when the user needs the product, and the user can purchase the product through relevant channel. In the process of delivering the advertisement video, the problem that brands and products cannot be displayed yet when users skip the advertisement video exists, the delivery effect of the advertisement video is poor, and therefore advertisement designers need to optimize the advertisement video.
However, before optimizing the advertisement video, the advertisement designer needs to think the advertisement optimization direction again, and starts to make the advertisement video after determining the optimization direction, so that the making period of the advertisement video is long, and much labor cost and time cost need to be consumed. Therefore, how to optimize the advertisement video quickly and accurately is a problem to be solved urgently at present.
Disclosure of Invention
The invention mainly aims to provide an advertisement video optimization method, device and equipment and a computer readable storage medium, aiming at quickly and accurately optimizing an advertisement video.
In order to achieve the above object, the present invention provides an advertisement video optimization method, which includes the following steps:
dividing an advertisement video to be optimized into a plurality of advertisement video segments, and extracting a key video frame of each advertisement video segment through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
obtaining a key index evaluation algorithm, and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
selecting a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame;
and acquiring a key video frame preposition strategy, and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain the target advertisement video.
Further, the step of evaluating each candidate key video frame of the candidate key video frames according to the key index evaluation algorithm to obtain the target key index of each candidate key video frame comprises:
acquiring character information contained in each candidate key video frame in the candidate key video frames;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm and the character information.
Further, the step of determining the target key index of each candidate key video frame according to the key index evaluation algorithm and the text information comprises:
calculating the entropy of the character information contained in each candidate key video frame, and calculating the similarity between the character information contained in each candidate key video frame and preset character information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the similarity.
Further, after the step of obtaining the text information included in each candidate key video frame of the plurality of candidate key video frames, the method further includes:
calculating the entropy of the text information contained in each candidate key video frame;
predicting an aesthetic score of each candidate key video frame in the plurality of candidate key video frames based on a preset aesthetic score prediction model;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the aesthetic score.
Further, after the step of predicting the aesthetic score of each candidate key video frame in the candidate key video frames based on the preset aesthetic score prediction model, the method further comprises:
calculating the similarity between the text information contained in each candidate key video frame and preset text information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information, the similarity and the aesthetic score.
Further, before the step of dividing the advertisement video to be optimized into a plurality of advertisement video segments, the method further includes:
when an algorithm strategy updating instruction is monitored, acquiring corresponding advertisement feedback data, a key index evaluation algorithm to be updated and a key video frame prepositive strategy according to the algorithm strategy updating instruction;
and executing updating operation on the key index evaluation algorithm to be updated and the key video frame preposition strategy according to the advertisement feedback data.
Further, the step of executing the updating operation to the key index evaluation algorithm to be updated and the key video frame pre-strategy according to the advertisement feedback data comprises:
acquiring a preset algorithm strategy updating model, and inputting the advertisement feedback data into the algorithm strategy updating model;
acquiring a first parameter value output by the algorithm strategy updating model and used for updating the key index evaluation algorithm and a second parameter value used for updating the key video frame pre-strategy;
updating the key index evaluation algorithm according to the first parameter value, and updating the key video frame pre-strategy according to the second parameter value.
In addition, to achieve the above object, the present invention also provides an advertisement video optimization apparatus, including:
the segment segmentation module is used for segmenting the advertisement video to be optimized into a plurality of advertisement video segments;
the video frame extraction module is used for extracting key video frames of each advertisement video clip through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
the key index evaluation module is used for acquiring a key index evaluation algorithm and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
a selection module, configured to select a target key video frame from the candidate key video frames according to a target key index of each candidate key video frame;
and the advertisement video optimization module is used for acquiring a key video frame preposition strategy and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain a target advertisement video.
In addition, to achieve the above object, the present invention also provides an advertisement video optimization apparatus, including: a memory, a processor and an advertising video optimization program stored on the memory and executable on the processor, the advertising video optimization program when executed by the processor implementing the steps of the advertising video optimization method as described above.
The present invention also provides a computer readable storage medium having stored thereon an advertisement video optimization program, which when executed by a processor, implements the steps of the advertisement video optimization method as described above.
The invention provides an advertisement video optimization method, device, equipment and computer readable storage medium, the invention divides an advertisement video into a plurality of advertisement video segments, extracts key video frames of each advertisement video segment to obtain a plurality of candidate key video frames, evaluates each candidate key video frame based on a key index evaluation algorithm to obtain a target key index of each candidate key video frame, selects a target key video frame from the candidate key video frames based on the target key index of each candidate key video frame, optimizes the advertisement video based on a key video frame preposition strategy and the target key video frame to obtain a target advertisement video, the whole process does not need an advertisement designer to think about the optimization direction again, can avoid the uncertainty of the advertisement designer, does not need to consume much time to make the advertisement video, meanwhile, the advertisement video is optimized based on key video frame extraction and key video frame preposition, so that the advertisement video can be quickly and accurately optimized, and the advertisement video delivery effect can be improved.
Drawings
FIG. 1 is a schematic diagram of an apparatus architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of an advertisement video optimization method according to the present invention;
FIG. 3 is a flowchart illustrating a fourth exemplary embodiment of an advertisement video optimization method according to the present invention;
fig. 4 is a functional block diagram of an advertisement video optimization apparatus according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
The advertisement video optimization device can be a PC (personal computer), and can also be a mobile terminal device with a display function, such as a smart phone, a tablet personal computer and a portable computer.
As shown in fig. 1, the advertisement video optimization apparatus may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the advertising video optimization device architecture shown in fig. 1 does not constitute a limitation of the advertising video optimization device and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an advertisement video optimization program.
In the advertisement video optimization device shown in fig. 1, the network interface 1004 is mainly used for connecting to a background server and communicating with the background server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and processor 1001 may be configured to invoke the ad video optimization program stored in memory 1005 and perform the following steps:
dividing an advertisement video to be optimized into a plurality of advertisement video segments, and extracting a key video frame of each advertisement video segment through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
obtaining a key index evaluation algorithm, and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
selecting a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame;
and acquiring a key video frame preposition strategy, and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain the target advertisement video.
Further, the processor 1001 may be configured to invoke an advertisement video optimization program stored in the memory 1005, and further perform the following steps:
acquiring character information contained in each candidate key video frame in the candidate key video frames;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm and the character information.
Further, the processor 1001 may be configured to invoke an advertisement video optimization program stored in the memory 1005, and further perform the following steps:
calculating the entropy of the character information contained in each candidate key video frame, and calculating the similarity between the character information contained in each candidate key video frame and preset character information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the similarity.
Further, the processor 1001 may be configured to invoke an advertisement video optimization program stored in the memory 1005, and further perform the following steps:
calculating the entropy of the text information contained in each candidate key video frame;
predicting an aesthetic score of each candidate key video frame in the plurality of candidate key video frames based on a preset aesthetic score prediction model;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the aesthetic score.
Further, the processor 1001 may be configured to invoke an advertisement video optimization program stored in the memory 1005, and further perform the following steps:
calculating the similarity between the text information contained in each candidate key video frame and preset text information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information, the similarity and the aesthetic score.
Further, the processor 1001 may be configured to invoke an advertisement video optimization program stored in the memory 1005, and further perform the following steps:
when an algorithm strategy updating instruction is monitored, acquiring corresponding advertisement feedback data, a key index evaluation algorithm to be updated and a key video frame prepositive strategy according to the algorithm strategy updating instruction;
and executing updating operation on the key index evaluation algorithm to be updated and the key video frame preposition strategy according to the advertisement feedback data.
Further, the processor 1001 may be configured to invoke an advertisement video optimization program stored in the memory 1005, and further perform the following steps:
acquiring a preset algorithm strategy updating model, and inputting the advertisement feedback data into the algorithm strategy updating model;
acquiring a first parameter value output by the algorithm strategy updating model and used for updating the key index evaluation algorithm and a second parameter value used for updating the key video frame pre-strategy;
updating the key index evaluation algorithm according to the first parameter value, and updating the key video frame pre-strategy according to the second parameter value.
The specific embodiment of the advertisement video optimization device of the present invention is substantially the same as the specific embodiments of the advertisement video optimization method described below, and details thereof are not repeated herein.
The invention provides an advertisement video optimization method.
Referring to fig. 2, fig. 2 is a flowchart illustrating a first embodiment of an advertisement video optimization method according to the present invention.
In this embodiment, the advertisement video optimization method includes:
step S101, dividing an advertisement video to be optimized into a plurality of advertisement video segments, and extracting key video frames of each advertisement video segment through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
in this embodiment, the advertisement video optimization method is applied to an advertisement video optimization device, which may be the device shown in fig. 1, and an advertisement video optimization program is installed in the advertisement video optimization device, when an advertisement video needs to be optimized, the advertisement video that needs to be optimized may be transmitted to the advertisement video optimization device, the transmission manner includes networking transmission (for example, transmitting the advertisement video to the advertisement video optimization device through a data network or a wireless network) and local transmission (for example, transmitting the advertisement video to the advertisement video optimization device through a data connection line, a usb disk, a hard disk, or the like), a user may select the advertisement video that needs to be optimized, after the user selects the advertisement video that needs to be optimized, the advertisement video optimization device obtains the advertisement video to be optimized, and divides the advertisement video to be optimized into a plurality of advertisement video segments, and extracting key video frames of each advertisement video clip through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames.
The advertisement video is divided by Shot Boundary Detection (SBD), and the advertisement video can be divided into a plurality of independent advertisement video segments by Shot boundary detection, and each advertisement video segment is composed of a plurality of video frames. Shot boundary detection algorithms include, but are not limited to, color histograms based on video frames, luminance values based on video frames, and edge features based on video frames. The preset video frame extraction algorithm includes, but is not limited to, a clustering algorithm and a recurrent neural network algorithm, and specifically, corresponding feature vectors are extracted from each video frame, and key video frame extraction is performed on each advertisement video clip based on the clustering algorithm or the recurrent neural network algorithm and the extracted feature vectors to obtain a plurality of candidate key video frames. The clustering algorithm does not need to be trained by a large amount of labeled video data and is suitable for scenes with few samples or no labeled data, the recurrent neural network algorithm needs to be trained by a large amount of labeled video data and is suitable for scenes with many samples and labeled data, and different algorithms can be selected based on actual application scenes.
Step S102, obtaining a key index evaluation algorithm, and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
in this embodiment, after obtaining a plurality of candidate key video frames, the advertisement video optimization device obtains a key index evaluation algorithm, and evaluates each candidate key video frame of the plurality of candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame. Specifically, the text information included in each candidate key video frame in the candidate key video frames is obtained, and according to the key index evaluation algorithm and the text information, the target key index of each candidate key video frame is determined, that is, the entropy (information amount) of the text information included in each candidate key video frame is calculated, the mapping relation table of the entropy of the pre-stored text information and the key index is queried, and the key index corresponding to the entropy of the text information included in each candidate key video frame is determined as the target key index of each candidate key video frame. The specific method for acquiring the text information contained in the candidate key video frames is to acquire the text information contained in each candidate key video frame through an OCR (Optical Character Recognition) algorithm, that is, perform denoising, binarization, tilt correction, Character cutting, Recognition and other processing on each candidate key video frame to acquire the text information in the candidate key video frames.
Specifically, the specific determination method of the target key index of the candidate key video frames may further be to calculate entropy of text information included in each candidate key video frame, calculate similarity between the text information included in each candidate key video frame and preset text information, determine the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy and the similarity of the text information, query a mapping relation table of pre-stored text information entropy and key index to obtain a first key index of each candidate key video frame, query a mapping relation table of pre-stored similarity and key index to obtain a second key index of each candidate key video frame, obtain a first weight coefficient and a second weight coefficient from the key index evaluation algorithm, and multiply the first weight coefficient by the first key index of each candidate key video frame, obtaining a first weight key index of each candidate key video frame, multiplying the second weight key index of each candidate key video frame by the second weight coefficient to obtain a second weight key index of each candidate key video frame, and determining the corresponding sum of the first weight key index of each candidate key video frame and the second weight key index of each candidate key video frame as the target key index of each candidate key video frame. It should be noted that the sum of the first weight coefficient and the second weight coefficient is 1, and the preset text information may be set based on an actual situation, which is not specifically limited in this embodiment.
Step S103, selecting a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame;
in this embodiment, after obtaining the key index of each candidate key video frame, the advertisement video optimization device selects a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame, that is, selects a candidate key video frame with the highest target key index from the candidate key video frames as the target key video frame.
And step S104, acquiring a key video frame preposition strategy, and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain the target advertisement video.
In this embodiment, after obtaining the target key video frame, the advertisement video optimization device obtains a key video frame pre-policy, and optimizes the advertisement video based on the key video frame pre-policy and the target key video frame to obtain the target advertisement video, that is, based on the key video frame pre-policy, the target key video frame is pre-positioned at a corresponding position of the advertisement video, and a corresponding playing time is set for the target key video frame to optimize the advertisement video. The key video frame pre-positioning policy includes a pre-positioning length and a playing time of a video frame, and it should be noted that the key video frame pre-positioning policy may be set based on an actual situation, which is not specifically limited in this embodiment.
In the embodiment, the invention divides the advertisement video into a plurality of advertisement video segments, extracts key video frames of each advertisement video segment to obtain a plurality of candidate key video frames, evaluates each candidate key video frame based on a key index evaluation algorithm to obtain a target key index of each candidate key video frame, selects a target key video frame from the candidate key video frames based on the target key index of each candidate key video frame, optimizes the advertisement video based on a key video frame pre-strategy and the target key video frame to obtain the target advertisement video, does not need an advertisement designer to think the optimization direction again in the whole process, can avoid the uncertainty of the advertisement designer, does not need to consume more time to produce the advertisement video, and simultaneously extracts and pre-optimizes the advertisement video based on the key video frames, the advertisement video can be quickly and accurately optimized, and the advertisement video putting effect can be improved.
Further, based on the first embodiment, a second embodiment of the advertisement video optimization method of the present invention is provided, which is different from the foregoing embodiments in that the specific determination manner of the target key index of each candidate key video frame may be further that after the text information included in each candidate key video frame is obtained, the advertisement video optimization apparatus calculates the entropy of the text information included in each candidate key video frame, predicts the aesthetic score of each candidate key video frame in a plurality of candidate key video frames based on a preset aesthetic score prediction model, and then determines the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the text information and the aesthetic score, that is, queries a mapping relation table between the pre-stored entropy of the text information and the key index to obtain the first key index of each candidate key video frame, and inquiring a mapping relation table of prestored aesthetic scores and key indexes to obtain a third key index of each candidate key video frame, then obtaining a first weight coefficient and a third weight coefficient from a key index evaluation algorithm, multiplying the first key index of each candidate key video frame by the first weight coefficient to obtain a first weight key index of each candidate key video frame, multiplying the third key index of each candidate key video frame by the third weight coefficient to obtain a third weight key index of each candidate key video frame, and finally determining the corresponding sum of the first weight key index of each candidate key video frame and the third weight key index of each candidate key video frame as the target key index of each candidate key video frame. It should be noted that the sum of the first weight coefficient and the third weight coefficient is 1, and specific values of the first weight coefficient and the third weight coefficient may be set based on actual conditions, which is not specifically limited in this embodiment.
The present embodiment is not particularly limited to this, specifically, feature extraction is performed on each candidate key video frame to obtain the aesthetic features of each candidate key video frame required by the aesthetic score prediction model, and the aesthetic features of each candidate key video frame are input to the aesthetic score prediction model to obtain the aesthetic score of each candidate key video frame.
In the embodiment, the target key index of the candidate key video frame is obtained by comprehensively evaluating the candidate key video frame based on the entropy of the character information contained in the candidate key video frame and the aesthetic score of the candidate key video frame, so that the reliability of the target key index can be greatly improved, and the target key video frame can be conveniently and accurately found out subsequently.
Further, based on the second embodiment, a third embodiment of the advertisement video optimization method of the present invention is provided, which is different from the previous embodiments in that after the aesthetic score of each candidate key video frame is obtained through prediction, the advertisement video optimization apparatus calculates the similarity between the text information and the preset text information included in each candidate key video frame, and determines the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy, the similarity and the aesthetic score of the text information, that is, queries the pre-stored mapping relationship table of the entropy of the text information and the key index to obtain the first key index of each candidate key video frame, and queries the pre-stored mapping relationship table of the similarity and the key index to obtain the second key index of each candidate key video frame, and queries the pre-stored mapping relationship table of the aesthetic score and the key index, obtaining a third key index of each candidate key video frame, then obtaining a first weight coefficient, a second weight coefficient and a third weight coefficient from a key index evaluation algorithm, multiplying the first key index of each candidate key video frame by the first weight coefficient to obtain a first weight key index of each candidate key video frame, multiplying the second key index of each candidate key video frame by the second weight coefficient to obtain a second weight key index of each candidate key video frame, multiplying the third key index of each candidate key video frame by the third weight coefficient to obtain a third weight key index of each candidate key video frame, and finally summing the first weight key index of each candidate key video frame, the second weight key index of each candidate key video frame and the third weight key index of each candidate key video frame, a target key index is determined for each candidate key video frame. It should be noted that the sum of the first weight coefficient, the second weight coefficient, and the third weight coefficient is 1, and specific values of the first weight coefficient, the second weight coefficient, and the third weight coefficient may be set based on actual situations, which is not specifically limited in this embodiment.
In the embodiment, the candidate key video frames are comprehensively evaluated based on the entropy of the character information contained in the candidate key video frames, the aesthetic score of the candidate key video frames and the similarity between the character information contained in the candidate key video frames and the preset character information to obtain the target key indexes of the candidate key video frames, so that the credibility of the target key indexes can be further improved, and the target key video frames can be conveniently and accurately found out subsequently.
Further, referring to fig. 3, a fourth embodiment of the advertisement video optimization method of the present invention is proposed based on the first, second, or third embodiment, and is different from the foregoing embodiment in that before the step S101, the method further includes:
step S105, when an algorithm strategy updating instruction is monitored, acquiring corresponding advertisement feedback data, a key index evaluation algorithm to be updated and a key video frame preposition strategy according to the algorithm strategy updating instruction;
and step S106, according to the advertisement feedback data, updating operation is executed on the key index evaluation algorithm to be updated and the key video frame preposition strategy.
In this embodiment, before the advertisement video to be optimized is divided into a plurality of advertisement video segments, there is a case that the key index evaluation algorithm and the key video frame pre-policy need to be updated, and for this reason, when an algorithm policy update instruction is monitored, the advertisement video optimization device obtains corresponding advertisement feedback data, the key index evaluation algorithm to be updated, and the key video frame pre-policy according to the algorithm policy update instruction, and then executes update operation on the key index evaluation algorithm to be updated and the key video frame pre-policy according to the advertisement feedback data. Advertisement feedback data includes, but is not limited to, click through rate, user registration rate, brand reach rate, product purchase rate, and advertisement viewing duration, among others.
Specifically, a preset algorithm strategy updating model is obtained, the advertisement feedback data is input into the algorithm strategy updating model, then a first parameter value output by the algorithm strategy updating model and used for updating the key index evaluation algorithm and a second parameter value used for updating the key video frame pre-strategy are obtained, finally the key index evaluation algorithm is updated according to the first parameter value, and the key video frame pre-strategy is updated according to the second parameter value. The algorithm strategy updating model is obtained by training advertisement feedback data with a large data volume, a first parameter value and a second parameter value, a specific training mode can be set based on an actual situation, which is not specifically limited in this embodiment, the first parameter value includes a value of a first weight coefficient, a value of a second weight coefficient and a value of a third weight coefficient, the second parameter value includes a value of a pre-length and a value of video playing time, that is, updating the key index evaluation algorithm is to update the value of the first weight coefficient, the value of the second weight coefficient and the value of the third weight coefficient in the key index evaluation algorithm, and update the key video frame pre-strategy is to update the value of the pre-length and the value of the video playing time in the key video frame pre-strategy.
In the embodiment, the key index evaluation algorithm and the key video frame pre-strategy are updated before the advertisement video is optimized, and the advertisement video can be accurately optimized by adopting a better key index evaluation algorithm and a better key video frame pre-strategy.
The invention also provides an advertisement video optimization device.
Referring to fig. 4, fig. 4 is a functional block diagram of an advertisement video optimization apparatus according to a first embodiment of the present invention.
In this embodiment, the advertisement video optimization apparatus includes:
a segment dividing module 101, configured to divide an advertisement video to be optimized into a plurality of advertisement video segments;
the video frame extraction module 102 is configured to perform key video frame extraction on each advertisement video clip through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
the key index evaluation module 103 is configured to obtain a key index evaluation algorithm, and evaluate each candidate key video frame in the plurality of candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
a selecting module 104, configured to select a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame;
and the advertisement video optimization module 105 is configured to acquire a key video frame pre-positioning strategy, and optimize the advertisement video based on the key video frame pre-positioning strategy and the target key video frame to obtain a target advertisement video.
Further, the key index evaluation module 103 is further configured to:
acquiring character information contained in each candidate key video frame in the candidate key video frames;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm and the character information.
Further, the key index evaluation module 103 is further configured to:
calculating the entropy of the character information contained in each candidate key video frame, and calculating the similarity between the character information contained in each candidate key video frame and preset character information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the similarity.
Further, the key index evaluation module 103 is further configured to:
calculating the entropy of the text information contained in each candidate key video frame;
predicting an aesthetic score of each candidate key video frame in the plurality of candidate key video frames based on a preset aesthetic score prediction model;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the aesthetic score.
Further, the key index evaluation module 103 is further configured to:
calculating the similarity between the text information contained in each candidate key video frame and preset text information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information, the similarity and the aesthetic score.
Further, the advertisement video optimization apparatus further includes:
the acquisition module is used for acquiring corresponding advertisement feedback data, a key index evaluation algorithm to be updated and a key video frame preposition strategy according to the algorithm strategy updating instruction when the algorithm strategy updating instruction is monitored;
and the updating module is used for executing updating operation on the key index evaluation algorithm to be updated and the key video frame preposition strategy according to the advertisement feedback data.
Further, the update module is further configured to:
acquiring a preset algorithm strategy updating model, and inputting the advertisement feedback data into the algorithm strategy updating model;
acquiring a first parameter value output by the algorithm strategy updating model and used for updating the key index evaluation algorithm and a second parameter value used for updating the key video frame pre-strategy;
updating the key index evaluation algorithm according to the first parameter value, and updating the key video frame pre-strategy according to the second parameter value.
The specific embodiment of the advertisement video optimization apparatus of the present invention is substantially the same as the embodiments of the advertisement video optimization method, and is not described herein again.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where an advertisement video optimization program is stored on the computer-readable storage medium, and when executed by a processor, the advertisement video optimization program performs the following steps:
dividing an advertisement video to be optimized into a plurality of advertisement video segments, and extracting a key video frame of each advertisement video segment through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
obtaining a key index evaluation algorithm, and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
selecting a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame;
and acquiring a key video frame preposition strategy, and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain the target advertisement video.
Further, when executed by the processor, the advertisement video optimization program performs the following steps:
acquiring character information contained in each candidate key video frame in the candidate key video frames;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm and the character information.
Further, when executed by the processor, the advertisement video optimization program performs the following steps:
calculating the entropy of the character information contained in each candidate key video frame, and calculating the similarity between the character information contained in each candidate key video frame and preset character information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the similarity.
Further, when executed by the processor, the advertisement video optimization program performs the following steps:
calculating the entropy of the text information contained in each candidate key video frame;
predicting an aesthetic score of each candidate key video frame in the plurality of candidate key video frames based on a preset aesthetic score prediction model;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the aesthetic score.
Further, when executed by the processor, the advertisement video optimization program performs the following steps:
calculating the similarity between the text information contained in each candidate key video frame and preset text information;
determining a target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the text information, the similarity and the aesthetic score
Further, when executed by the processor, the advertisement video optimization program performs the following steps:
when an algorithm strategy updating instruction is monitored, acquiring corresponding advertisement feedback data, a key index evaluation algorithm to be updated and a key video frame prepositive strategy according to the algorithm strategy updating instruction;
and executing updating operation on the key index evaluation algorithm to be updated and the key video frame preposition strategy according to the advertisement feedback data.
Further, when executed by the processor, the advertisement video optimization program performs the following steps:
acquiring a preset algorithm strategy updating model, and inputting the advertisement feedback data into the algorithm strategy updating model;
acquiring a first parameter value output by the algorithm strategy updating model and used for updating the key index evaluation algorithm and a second parameter value used for updating the key video frame pre-strategy;
updating the key index evaluation algorithm according to the first parameter value, and updating the key video frame pre-strategy according to the second parameter value.
The specific embodiment of the computer-readable storage medium of the present invention is substantially the same as the embodiments of the advertisement video optimization method, and is not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. An advertisement video optimization method, characterized in that the advertisement video optimization method comprises the following steps:
dividing an advertisement video to be optimized into a plurality of advertisement video segments, and extracting a key video frame of each advertisement video segment through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
obtaining a key index evaluation algorithm, and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
selecting a target key video frame from the candidate key video frames according to the target key index of each candidate key video frame;
acquiring a key video frame pre-strategy, and optimizing the advertisement video based on the key video frame pre-strategy and the target key video frame to obtain a target advertisement video, wherein the key video frame pre-strategy comprises the pre-length and the playing time of the target key video frame;
the step of evaluating each candidate key video frame of the plurality of candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame comprises:
acquiring character information contained in each candidate key video frame in the candidate key video frames;
calculating the entropy of the character information contained in each candidate key video frame, and calculating the similarity between the character information contained in each candidate key video frame and preset character information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the similarity.
2. The method for optimizing advertisement video according to claim 1, wherein after the step of obtaining the text information included in each of the plurality of candidate key video frames, the method further comprises:
calculating the entropy of the text information contained in each candidate key video frame;
predicting an aesthetic score of each candidate key video frame in the plurality of candidate key video frames based on a preset aesthetic score prediction model;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the aesthetic score.
3. The advertisement video optimization method of claim 2, wherein the step of predicting the aesthetic score of each candidate key video frame of the plurality of candidate key video frames based on the preset aesthetic score prediction model is followed by further comprising:
calculating the similarity between the text information contained in each candidate key video frame and preset text information;
and determining the target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information, the similarity and the aesthetic score.
4. The advertisement video optimization method of any of claims 1-3, wherein the step of segmenting the advertisement video to be optimized into advertisement video segments is preceded by the step of:
when an algorithm strategy updating instruction is monitored, acquiring corresponding advertisement feedback data, a key index evaluation algorithm to be updated and a key video frame prepositive strategy according to the algorithm strategy updating instruction;
and executing updating operation on the key index evaluation algorithm to be updated and the key video frame preposition strategy according to the advertisement feedback data.
5. The advertisement video optimization method of claim 4, wherein the step of performing an update operation on the key index evaluation algorithm and the key video frame pre-strategy to be updated according to the advertisement feedback data comprises:
acquiring a preset algorithm strategy updating model, and inputting the advertisement feedback data into the algorithm strategy updating model;
acquiring a first parameter value output by the algorithm strategy updating model and used for updating the key index evaluation algorithm and a second parameter value used for updating the key video frame pre-strategy;
updating the key index evaluation algorithm according to the first parameter value, and updating the key video frame pre-strategy according to the second parameter value.
6. An advertisement video optimization apparatus, comprising:
the segment segmentation module is used for segmenting the advertisement video to be optimized into a plurality of advertisement video segments;
the video frame extraction module is used for extracting key video frames of each advertisement video clip through a preset video frame extraction algorithm to obtain a plurality of candidate key video frames;
the key index evaluation module is used for acquiring a key index evaluation algorithm and evaluating each candidate key video frame in the candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame;
the step of evaluating each candidate key video frame of the plurality of candidate key video frames according to the key index evaluation algorithm to obtain a target key index of each candidate key video frame comprises:
acquiring character information contained in each candidate key video frame in the candidate key video frames;
calculating the entropy of the character information contained in each candidate key video frame, and calculating the similarity between the character information contained in each candidate key video frame and preset character information;
determining a target key index of each candidate key video frame according to the key index evaluation algorithm, the entropy of the character information and the similarity;
a selection module, configured to select a target key video frame from the candidate key video frames according to a target key index of each candidate key video frame;
and the advertisement video optimization module is used for acquiring a key video frame preposition strategy, and optimizing the advertisement video based on the key video frame preposition strategy and the target key video frame to obtain a target advertisement video, wherein the key video frame preposition strategy comprises the prepositive length and the playing time of the target key video frame.
7. An advertisement video optimization device, characterized in that the advertisement video optimization device comprises: memory, a processor and an advertising video optimization program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the advertising video optimization method of any one of claims 1 to 5.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon an advertisement video optimization program, which when executed by a processor implements the steps of the advertisement video optimization method according to any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910140441.4A CN109922379B (en) | 2019-02-22 | 2019-02-22 | Advertisement video optimization method, device and equipment and computer readable storage medium |
| PCT/CN2019/078528 WO2020168606A1 (en) | 2019-02-22 | 2019-03-18 | Advertisement video optimising method, apparatus and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910140441.4A CN109922379B (en) | 2019-02-22 | 2019-02-22 | Advertisement video optimization method, device and equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109922379A CN109922379A (en) | 2019-06-21 |
| CN109922379B true CN109922379B (en) | 2022-01-04 |
Family
ID=66962344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910140441.4A Active CN109922379B (en) | 2019-02-22 | 2019-02-22 | Advertisement video optimization method, device and equipment and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109922379B (en) |
| WO (1) | WO2020168606A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104370A (en) * | 2019-12-18 | 2020-05-05 | 北京大龙得天力广告传媒有限公司 | Advertisement video storage system and method |
| CN111294646B (en) * | 2020-02-17 | 2022-08-30 | 腾讯科技（深圳）有限公司 | Video processing method, device, equipment and storage medium |
| CN113610557A (en) * | 2021-07-09 | 2021-11-05 | 苏州众言网络科技股份有限公司 | Advertisement video processing method and device |
| CN113378002B (en) | 2021-08-11 | 2022-01-21 | 北京达佳互联信息技术有限公司 | Information delivery method and device, electronic equipment and storage medium |
| CN114697762B (en) * | 2022-04-07 | 2023-11-28 | 脸萌有限公司 | Processing method, processing device, terminal equipment and medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7889794B2 (en) * | 2006-02-03 | 2011-02-15 | Eastman Kodak Company | Extracting key frame candidates from video clip |
| US20090094113A1 (en) * | 2007-09-07 | 2009-04-09 | Digitalsmiths Corporation | Systems and Methods For Using Video Metadata to Associate Advertisements Therewith |
| CN104581380B (en) * | 2014-12-30 | 2018-08-31 | 联想(北京)有限公司 | A kind of method and mobile terminal of information processing |
| CN107172481A (en) * | 2017-05-09 | 2017-09-15 | 深圳市炜光科技有限公司 | Video segment splices method of combination and system |
| CN107392666A (en) * | 2017-07-24 | 2017-11-24 | 北京奇艺世纪科技有限公司 | Advertisement data processing method, device and advertisement placement method and device |
| CN108632641A (en) * | 2018-05-04 | 2018-10-09 | 百度在线网络技术（北京）有限公司 | Method for processing video frequency and device |
| CN109121021A (en) * | 2018-09-28 | 2019-01-01 | 北京周同科技有限公司 | A kind of generation method of Video Roundup, device, electronic equipment and storage medium |
| CN109194978A (en) * | 2018-10-15 | 2019-01-11 | 广州虎牙信息科技有限公司 | Live video clipping method, device and electronic equipment |
-
2019
- 2019-02-22 CN CN201910140441.4A patent/CN109922379B/en active Active
- 2019-03-18 WO PCT/CN2019/078528 patent/WO2020168606A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN109922379A (en) | 2019-06-21 |
| WO2020168606A1 (en) | 2020-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109922379B (en) | Advertisement video optimization method, device and equipment and computer readable storage medium | |
| CN109145204B (en) | Portrait label generation and use method and system | |
| US20160239865A1 (en) | Method and device for advertisement classification | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| US11593860B2 (en) | Method, medium, and system for utilizing item-level importance sampling models for digital content selection policies | |
| US10657559B2 (en) | Generating and utilizing a conversational index for marketing campaigns | |
| US20110117537A1 (en) | Usage estimation device | |
| CN110599393B (en) | Picture style conversion method, device, equipment and computer readable storage medium | |
| US20110196739A1 (en) | Systems and methods for efficiently ranking advertisements based on relevancy and click feedback | |
| CN111159570B (en) | Information recommendation method and server | |
| CN108230114B (en) | Method, device and equipment for selecting user feature tag and readable storage medium | |
| CN110675179A (en) | Marketing information processing method and device, electronic equipment and readable storage medium | |
| CN111475628A (en) | Session data processing method, device, computer equipment and storage medium | |
| CN113869063A (en) | Data recommendation method and device, electronic equipment and storage medium | |
| CN106570003B (en) | Data pushing method and device | |
| CN108197288B (en) | House source pushing method, device, equipment and medium according to user characteristic preference | |
| CN111652219A (en) | Image-text identification detection and identification method and device, server and storage medium | |
| CN110750718A (en) | User guiding method, device, equipment and storage medium based on recommendation system | |
| CN113127720A (en) | Hot word searching determination method and device | |
| KR20210052746A (en) | Method, apparatus and computer program for estimating sales volume of content to be productized | |
| CN113886628A (en) | Image retrieval method, device and storage medium | |
| CN110275986B (en) | Video recommendation method based on collaborative filtering, server and computer storage medium | |
| CN112905892A (en) | Big data processing method and big data server applied to user portrait mining | |
| CN109902531B (en) | User management method, device, medium and electronic equipment | |
| CN110795620A (en) | Product recommendation method, device, equipment and storage medium based on same type of users |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |