WO2018108047A1

WO2018108047A1 - Method and device for generating information displaying image

Info

Publication number: WO2018108047A1
Application number: PCT/CN2017/115416
Authority: WO
Inventors: 曾佩玲
Original assignee: 腾讯科技（深圳）有限公司
Priority date: 2016-12-15
Filing date: 2017-12-11
Publication date: 2018-06-21
Also published as: CN106528884B; CN106528884A

Abstract

A method and device for generating an information displaying image. The method comprises: dividing a target video determined by a terminal into a plurality of video frames (201); determining, according to a user characteristic, N target frames corresponding to respective users, wherein the target frames belong to video frames (202); determining users having M identical target frames as the same type of users (203); classifying the same type of users into M groups, and performing, by the M groups of users, a control experiment test on images corresponding to the M identical target frames (204); and determining, according to a result of the control experiment test, a target image having a highest click-through rate (CTR) of images corresponding to the M identical target frames, and employing the target image as the information displaying image for the same type of users (205).

Description

Method and device for generating information display picture

This application claims the priority of the Chinese Patent Application filed on Dec. 15, 2016, the Chinese Patent Application No. 201611163080.8, entitled "A Method and Apparatus for Generating Information Display Images", the entire contents of which are incorporated herein by reference. In the application.

Technical field

The present invention relates to the field of computer applications, and in particular, to a method and an apparatus for generating an information display picture.

Background technique

When a user clicks into the video website or opens the application (APP, Application) of the video website, he will see several pictures related to the corresponding video. The main purpose of these pictures is to display information related to the video to attract the user to click to enter the video. Such images are called operational images of video products. How to choose a running image has a significant impact on the amount of video clicks, so how to make a better-performing operational image is a more concerned issue for video sites or video producers.

At present, the operation pictures of video products are usually mainly made by hand. Generally, the pictures are taken out from the video content, or the promotional pictures of some TV dramas or movies. After manually selecting the operation pictures, the operation pictures are placed in the corresponding videos. On the website, for users to view the operation picture.

Since the prior art adopts a method of manually creating a picture, the created operation picture can only be applied to the video product itself, and the operation pictures seen by each user in the prior art are the same, but in the actual scene. Different users have different preferences. For the same video content, the information that different users want to obtain is different. However, the artificially produced operation pictures in the prior art are less targeted and cannot be targeted for each user. Provides valid information about the content of the video. Take video content for TV dramas. For example, some serial TV series will have updated story every day, so there will be new video content. If you want to update the operation picture of the TV series with the story, you need a lot of manpower.

Summary of the invention

The embodiment of the invention provides a method and a device for generating an information display picture, which are used to automatically generate different information display pictures for different categories of users, improve the click volume of the picture, provide effective information for more users, and save manpower.

In view of this, an embodiment of the present invention provides a method for generating an information display picture, including:

Segmenting the target video into a number of video frames;

Determining N target frames corresponding to each user according to user characteristics, where the target frame belongs to the video frame, and the N is an integer greater than 1;

Determining a user having M identical target frames as a homogeneous user, the M being an integer, and 1 < M ≤ N;

Dividing the same type of users into M groups, and performing a comparison experiment test on the pictures corresponding to the M identical target frames by the users of the M group;

Determining, according to the result of the comparison experiment test, a target picture with the highest click-through rate CTR in the picture corresponding to the M identical target frames, and displaying the picture as the information of the same-type user.

An embodiment of the present invention provides an apparatus for generating an information display picture, including:

a segmentation module, configured to divide the target video into a plurality of video frames;

a first determining module, configured to determine, according to user characteristics, N target frames corresponding to each user, where the target frame belongs to the video frame, and the N is an integer greater than one;

a second determining module, configured to determine a user having M identical target frames as a user of the same type, where M is an integer, and 1 < M ≤ N;

a test module, configured to divide the similar users determined by the second determining module into M groups, and perform a comparison experiment test on the pictures corresponding to the M identical target frames by the users of the M group;

a third determining module, configured to determine, according to the result of the comparison experiment test, a target picture with the highest click-through rate CTR in the picture corresponding to the M identical target frames, and display the target picture as the information of the same-type user image.

Another aspect of an embodiment of the present invention provides a computer readable storage medium having stored therein instructions that, when run on a computer, cause the computer to perform the methods described in the above aspects.

Another embodiment of the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the methods described in the various aspects above.

An embodiment of the present invention further provides a terminal, where the terminal includes: a processor, a memory; the memory is configured to store an instruction; the processor is configured to execute the instruction in the memory, so that the terminal The method of any of the preceding aspects is performed.

It can be seen from the above technical solutions that the embodiments of the present invention have the following advantages:

The embodiment of the present invention may divide the target video into a plurality of video frames, determine N target frames corresponding to each user according to user characteristics, and determine users with M identical target frames as users of the same class, for each class. The user divides the user into M groups, and the users of the M group are used as test users, and the pictures corresponding to the M target frames shared by the users are tested in a controlled experiment, and the highest click rate is determined according to the test results of the control experiment. One or more target images, and the one or more target images are displayed as information for such users. It can be seen that the solution can automatically generate information display pictures, and can classify users according to user characteristics, generate different information display pictures for different categories of users, and display different information according to user characteristics to different categories of users, which is more targeted. Improve image clicks, provide effective information to more users, and save manpower.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings which are used in the description of the embodiments will be briefly described. It is obvious that the drawings in the following description are only some embodiments of the present invention.

1 is a schematic diagram of an embodiment of an information display picture generating system in an embodiment of the present invention;

2 is a flowchart of an embodiment of a method for generating an information display picture according to an embodiment of the present invention;

FIG. 3 is a flowchart of another embodiment of a method for generating an information display picture according to an embodiment of the present invention; FIG.

4 is a schematic diagram of an embodiment of an apparatus for generating information display pictures according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of another embodiment of an apparatus for generating an information display picture according to an embodiment of the present invention; FIG.

FIG. 6 is a schematic diagram of another embodiment of an apparatus for generating an information display picture according to an embodiment of the present invention; FIG.

FIG. 7 is a schematic diagram of another embodiment of an apparatus for generating an information display picture according to an embodiment of the present invention; FIG.

FIG. 8 is a schematic diagram of another embodiment of an apparatus for generating an information display picture according to an embodiment of the present invention; FIG.

FIG. 9 is a schematic diagram of another embodiment of an apparatus for generating an information display picture according to an embodiment of the present invention.

detailed description

The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments.

The terms "first", "second", "third", "fourth", etc. (if present) in the specification and claims of the present invention and the above figures are used to distinguish similar objects without being used for Describe a specific order or order. It should be understood that the data used in this way can be interchanged where appropriate, so here The described embodiments of the invention can be implemented, for example, in a sequence other than those illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

In order to facilitate the understanding of the embodiments of the present invention, the following is a detailed description of the scenarios in which the embodiments of the present invention are applied. Referring first to FIG. 1 , a method for generating an information display image according to an embodiment of the present invention is shown. Schematic diagram of the system composition.

As shown in FIG. 1, the system may include a service system composed of at least one server 101, and a plurality of terminals 102. The server 101 in the service system may store data for generating an information display picture, and transmit the generated information display picture to the terminal. The terminal 102 can be used to upload the target video data that needs to generate the information display picture to the server 101, and display the information display picture returned by the server 101. It can be understood that the terminal 102 is not limited to the personal computer (PC, Personal Computer) shown in FIG. 1 , and may be another device capable of acquiring and displaying information display pictures, such as a mobile phone or a tablet computer.

For example, the user can upload the target video to the server through the terminal, and the server generates the information display image corresponding to the different types of users by using the information display image generation method in the embodiment of the present invention, and returns the user registered on the terminal to each terminal. The matching information shows the picture, and the terminal presents the information display picture returned by the server to the user.

It can be understood that the method and the device for generating the information display image in the embodiment of the present invention are applicable to other scenarios, such as an interaction scenario between a single server and a single terminal, and the server may be a single terminal. The user returns a message to display the image, and the terminal displays the information displayed by the server and presents the image to the user, which is not limited herein. In order to facilitate the understanding of the embodiments of the present invention, some terms in the embodiments of the present invention are introduced below:

The control experiment test can also be called the AB test. In the embodiment of the present invention, the meaning of the control experiment test and the AB test are the same. In short, it is to formulate two programs for the same target (for example, two Pages), let some users use the A plan, and the other part use the B plan to record the user's usage and determine which solution is more in line with the design requirements. When actually conducting the control experiment test, the following two methods may be included, one is that the technician makes multiple pages (or other elements for testing, such as pictures), and then sorts the traffic by URL redirection, and the other one One method is to test the software through a professional controlled experiment. The former requires more manpower and material resources, and the data analysis is more troublesome, while the latter does not require any programming technology, and can basically be realized by the editors that come with the software. Visual testing tools for the mainstream include: Google Website Optimizer, Visual Website Optimizer, Unbounce and Performable, Vertster, SiteSpect, Webtrends Optimize and Omniture's Test&Target, AB Tester, AppAdhoc Optimizer, etc., depending on the application scenario, determine the test tool used, here Not limited.

A video frame is a single image of the smallest unit in an image animation. Among them, a video frame of one frame is a pair of still pictures, and continuous frames form an animation, such as a television image. Each frame is a still image, and displaying multiple frames in rapid succession creates an illusion of motion.

Key frames, any animation to show motion or change, at least two different key states are given before and after, and the intermediate state changes and the connection terminal can be automatically completed. For example, in the Flash animation, the frame representing the key state can be defined. For keyframes.

Lens data refers to a piece of video data captured by the camera at one time. It is the basic physical unit of video structuring.

K-means clustering is a typical distance-based clustering algorithm. Distance is used as the evaluation index of similarity, that is, the closer the distance between two objects is, the greater the similarity is. The algorithm considers clusters to be composed of objects that are close together, thus making compact and independent clusters the ultimate goal. The working principle of the algorithm is to input the number of clusters k and the database containing n data objects, and finally output k clusters satisfying the minimum standard of variance. The k clusters have the following characteristics: each cluster itself is as compact as possible, and each cluster is separated as much as possible. The specific processing is as follows: First, k objects are arbitrarily selected from n data objects as the initial cluster center; and for other objects remaining, they are respectively allocated according to their similarity (ie distance) to these cluster centers. Give the most similar cluster (represented by the cluster center); then calculate the cluster center of each new cluster obtained (the mean of all objects in the cluster); repeat this process until the standard measure function Start to converge. For example, the mean square error can be used as a standard measure function.

Click-Through-Rate (CTR, click-Through-Rate) is a commonly used term for Internet advertising. The click-through rate of an online ad (such as an image ad/text ad/keyword ad/ranking ad/video ad, etc.) is the actual number of clicks on the ad divided by the show content. CTR is an important measure of the effectiveness of Internet advertising, where the actual number of clicks can be the number of pages that reach the target.

It can be understood that the method and device for generating information display pictures in the embodiments of the present invention are applicable to the operation picture production of the video content mentioned above, and can also be applied to other video related Internet pictures, such as movie poster production. This is not a limitation.

Based on the above background, a method for generating an information display picture in the embodiment of the present invention is first introduced. Referring to FIG. 2, an embodiment of a method for generating an information display picture in the embodiment of the present invention includes:

201. Split the target video into a plurality of video frames.

When the user needs to create the information display image of the target video, the target video is first input into the terminal, and the target video may be determined by the terminal according to the input video of the user, and the device for generating the information display image may be implemented by the terminal, and the information display image is The generating device can acquire the target video and divide the target video into a plurality of video frames. The target video may be one or more video sequences, such as a movie, a few episodes of a TV series or other video content, which is not limited herein, and the information display image may refer to an advertisement image of the target video, an operation image, or other A picture for displaying the content of the target video, which is not limited herein.

202. Determine N target frames corresponding to each user according to user characteristics.

The information display image generating device divides the target video into a plurality of video frames, and determines N target frames corresponding to each user according to the user characteristics, where the user features refer to characteristics of the user who operates the terminal to view the video content. For example, the user characteristics may indicate the user's preference for some video content, and the like. The target frame is selected from a plurality of video frames corresponding to the target video, and the number N of the target frames is an integer greater than 1. The specific value may be set by a user or a system, and is not limited herein. 203. Determine a user having M identical target frames as a similar user.

After the information display device determines the target frame corresponding to each user, the user having the M identical target frames is determined to be the same type of user, and the users with the M identical target frames are classified into the same class, and M is an integer, and 1 <M ≤ N, M specific value can be set by the user or the system, which is not limited herein. When M is equal to N, all users whose target frames are the same are classified into the same class. When M is not equal to N, for example, M is equal to 2, then there may be that user A and user B have two identical target frames a and b, and user A and user C also have two identical target frames c and d, which It can be considered that A and B are similar users. It can also be considered that A and C are similar users, but User A will only be classified as one of them, and will not appear in two or more user categories at the same time. It can be understood that when M is another value that is not equal to N, the processing procedure is similar to the above when a similar situation occurs, and will not be described again.

204. Divide the same type of users into M groups, and perform a comparison experiment test on the pictures corresponding to the M identical target frames by the users of the M group.

For each type of user, the user is divided into M groups, and the user of the M group performs a comparison experiment test on the pictures corresponding to the M identical target frames shared by the users, that is, the AB test can be performed. Specifically, the generating device of the information display image may divide the users classified into the same class into M groups in a random equal amount manner, and randomly assign the pictures corresponding to the M identical target frames shared by the users to the users of the M group. For each group of pictures, a control experiment can be performed. Then, the click pass rate of each group of users corresponding to the picture of the group of users is counted. It can be understood that, in addition to the random equal-packet mode, the device for generating the information display image can be divided into M groups by other means in other manners, which is not limited herein.

205. Determine, according to the result of the comparison experiment test, a target picture with the highest click-through rate among the pictures corresponding to the M identical target frames, and display the target picture as the information of the same user.

For each type of user, after comparing the M pictures corresponding to the user, the click pass rate of each picture is counted, and the target picture with the highest CTR among the M pictures corresponding to each type of user is determined, and The target image is displayed as a picture of the user of the class. It should be noted that, in the embodiment of the present invention, there may be one or more target pictures, which are not limited herein.

The embodiment of the present invention may divide the target video into a plurality of video frames, determine N target frames corresponding to each user according to user characteristics, and determine users with M identical target frames as users of the same class, for each class. The user divides the user into M groups, and the users of the M group are used as test users, and the pictures corresponding to the M target frames shared by the users are tested in a controlled experiment, and the highest click rate is determined according to the test results of the control experiment. One or more target images, and the one or more target images are displayed as information for such users. It can be seen that the embodiment of the present invention can automatically generate an information display picture, and can classify users according to user characteristics, generate different information display pictures for different categories of users, and display different information to different categories of users according to user characteristics, and more specifically Sex, can increase the amount of image clicks, provide more information for more users, and save manpower.

Based on the foregoing embodiment corresponding to FIG. 2, the target video may be divided into video frames in multiple manners, and the manner of determining the target frame is different according to different segmentation manners, and one of the following methods is taken as an example. The method for generating the information display picture in the embodiment of the present invention is described in detail. Referring to FIG. 3, another embodiment of a method for generating an information display picture in the embodiment of the present invention includes:

301. Split the target video into several pieces of lens data.

When the user needs to create the information display image of the target video, the target video is first input into the terminal, and the information display device generates the target video, and divides the target video into several lens data, which may be according to the distance of the color space or The other parameters are divided, which is not limited herein. The target video may be one or more video sequences, such as a movie, a few episodes of a TV series or other videos, which are not limited herein. The information display image may refer to an advertisement image of a target video, an operation image, or the like. Display the image of the target video content, which is not limited here.

302. Divide each lens data into a plurality of sub-lens data.

After the target video is segmented into a plurality of lens data, each lens data is further divided into sub-lens data, which may be divided according to other parameters such as the camera motion direction, which is not limited herein.

303. Divide each sub-lens data into a plurality of video frames.

The information display picture generating device divides each shot data into a plurality of sub-shot data, and further divides each sub-lens data into a plurality of video frames.

304. Determine L sub-shot data corresponding to each user according to user characteristics.

The information display picture generating device divides each shot data into a plurality of sub-shot data, and determines L sub-shot data corresponding to each user according to user characteristics, and L is an integer equal to or greater than 1.

Specifically, the generating device of the information display image may determine, for each user, the target sub-shot data of the tag information corresponding to the user in the sub-shot data included in the target video, and determine the preset sub-shot weight ranking in the target sub-shot data. The first L sub-lens data.

It should be noted that the preset sub-lens weight in the embodiment of the present invention may be determined by: the information display image generating device divides each sub-lens data into several video frames, according to the duration of the sub-shot corresponding duration That is, according to the number of video frames included in the sub-shot as the weight of the sub-lens. In addition to the number of video frames, the weight of the sub-lens may be further determined according to the weight of the video frame included in the sub-lens, and may be determined according to other parameters, which is not limited herein.

It should be noted that the tag information corresponding to the user in the embodiment of the present invention may be the name of the actor in the user tag, may be the director name in the user tag, may be the movie type in the user identifier, or may be in the user tag. Other information is not limited here. It can be understood that if the user does not have corresponding label information, the information display image generating device can directly adjust the preset sub-lens weights. The top L sub-shot data is used as the L sub-shot data corresponding to the user. If the number M of the target sub-lens data is less than L, then after the generating device of the information display image selects all the target sub-shot data, the remaining LM target sub-shot data are then sub-lens data corresponding to the target video according to the preset sub-lens weight. Select.

It can be understood that, in addition to the label information corresponding to the user, the information display image generating device may further determine the target sub-shot data according to the user-viewed video information, the user-collected video information, the user-searched keyword, and the like. The details are not limited herein.

305. Determine, according to the preset frame weight, a target frame corresponding to each sub-shot data in the L sub-shot data.

After the information display device determines the L sub-shot data corresponding to each user, the target frame corresponding to each of the L sub-shot data is determined according to the preset frame weight.

It can be understood that the preset frame weight is determined by the information generating device that divides the sub-lens data into a plurality of video frames, which may be specifically performed by using K-means clustering for each sub-shot data. The video frames in the sub-shot data are divided into K categories, and the video frames closest to the cluster center in each type of video frames are determined as key frames of the video frames, and the frame weights corresponding to each key frame are determined according to the frame parameters. The frame parameters include the proportion of the face, or the direction of the camera movement, or the focal length of the camera, or whether the camera is swayed, or other parameters, specifically combined with the application scene to select the specific composition of the frame parameters.

Correspondingly, after the frame weight is determined according to the foregoing manner, the information display image generating device may determine a key frame included in each of the L sub-shot data, and determine a key frame included in each sub-shot data for the L sub-lens data. One or more video frames with the largest frame weight, and the one or more video frames may serve as the target frame corresponding to the sub-shot data.

It can be understood that, if the generating device of the information display picture selects the target frame, the video frame with the largest weight in the key frame is the target frame of the sub-lens data, and the number of the target frames corresponding to each user is L, that is, N is equal to L. If the generating device of the information display picture selects the target frame, the K video frames with the largest weight in the key frame are used as the target frames of the sub-lens data, and the number of target frames corresponding to each user is K*L. , that is, N=K*L, * indicates multiplication, and K is an integer greater than 1.

In addition to the above manner, the device for generating the information display image may determine the frame weight and the target frame by other means, which is not limited herein.

306. Determine a user having M identical target frames as a similar user.

After the information display picture generating device determines the target frame corresponding to each user, it will have M identical The user of the target frame is determined to be a user of the same type, and the users of the same target frame are classified into the same class, and M is an integer, and 1<M ≤ N. The specific value can be set by the user or the system, which is not limited herein. When M is equal to N, all users whose target frames are the same are classified into the same class. When M is not equal to N, for example, M is equal to 2, then there may be that user A and user B have two identical target frames a and b, and user A and user C also have two identical target frames c and d, which It can be considered that A and B are similar users, and A and C can be considered as similar users, but A will only be classified as one of them, and will not appear in two or more user categories at the same time. It can be understood that when M is another value that is not equal to N, the processing procedure is similar to the above when a similar situation occurs, and will not be described again.

307. Divide the same type of users into M groups, and perform a comparison experiment test on the pictures corresponding to the M identical target frames by the users of the M group.

For each type of user, the users of the class are divided into M groups, and the users corresponding to the M identical target frames shared by the users of the M group are tested by the experimental experiment. Specifically, the device for generating the information display picture divides the users classified into the same class into M groups in a random equal amount manner, and randomly assigns the pictures corresponding to the M identical target frames shared by the users to the users of the M group. One for each group, perform AB. Then, the click pass rate of each group of users corresponding to the picture of the group of users is counted. It can be understood that, in addition to the random equal-packet mode, the device for generating the information display image can be divided into M groups by other means in other manners, which is not limited herein.

308. Determine, according to the result of the comparison experiment test, the target picture with the highest click-through rate among the pictures corresponding to the M identical target frames, and display the target picture as the information of the same user.

For each type of user, after comparing the M pictures corresponding to the user, the click pass rate of each picture is counted, and the target picture with the highest CTR among the M pictures corresponding to each type of user is determined, and The target image is displayed as a picture of the user of the class. It should be noted that, in the embodiment of the present invention, there may be one or more target pictures, which are not limited herein. Specifically, when the target image is multiple, the information display image generating device may perform rendering and layout of the plurality of target images into one image, and display the combined image as information of the user of the type. image. It can be understood that, when the target image is multiple, the information display image generating device may further process the plurality of target images by other methods to obtain information display images corresponding to the user.

It can also be understood that, in the embodiment of the present invention, after the target image is displayed as the information of the same user, the information display image generating device may further update the information display image according to the preset rule. The preset rule refers to a preset update rule, which may be a time period, that is, periodically updating the rule. The information display picture, such as updating once a week, updating once a month, etc., may be to achieve a trigger condition. For example, each time the TV series is updated, the information display picture is updated once, and other rules may be used, which are not limited herein.

The embodiment of the invention provides a specific manner of dividing a target video into a plurality of video frames, and improves the achievability of the solution. The embodiments of the present invention provide various manners for determining a target frame, which improves the flexibility of the solution. Further, the embodiment of the present invention can update the information display picture, and further improve the validity of the information provided by the information display picture.

For ease of understanding, the method for generating the information display picture in the embodiment of the present invention is described in detail in an application scenario:

The user can input two videos (ie, target video) of the first episode and the second episode of the TV drama "Da Jang Geum" to the terminal, and the generating device divides the two videos into six lens data according to the distance of the color space, and then divides the video The six lens data are divided into 24 sub-lens data according to the moving direction of the camera, and the 24 sub-lens data is divided into 100 video frames.

Suppose there are 1000 users, and the tag information corresponding to 200 users is Li Yingai, which is recorded as user 1 to 200; the tag information corresponding to 400 users is Chi Jinxi, which is recorded as user 201-600; the other 40 users do not. Set the label information and record it as user 601 to 1000. The generating device determines that the 24 sub-shot data corresponding to the target video includes 20 sub-lens data of Li Yingai (target sub-shot data), and 18 sub-lens data including Chi Jinxi (target sub-shot data), the generating device Determine the sub-shot data of the top 4 (L=4) of the preset sub-lens weights in the 20 sub-shot data of Li Yingai, respectively, a, b, c, d; determine the top 4 weights in the 18 sub-shot data including Chi Jinxi (L=4) sub-shot data, respectively, c, d, e, f; determine the target view Among the 24 sub-shot data corresponding to the frequency, the sub-lens data of the first 4 (L=4) of the preset sub-lens weights are respectively a, b, e, f. Then, the sub-lens data a, b, c, d is the four sub-lens data corresponding to the user of 1 to 200, and the sub-lens data c, d, e, f is the four sub-lens data corresponding to the user of 201 to 600, The lens data a, b, e, and f are the four sub-lens data corresponding to the users of 601 to 1000.

The generating device determines that the target frame with the largest frame weight in the sub-shot data a is a1, the target frame with the largest frame weight in the sub-shot data b is b1, and the target frame with the largest frame weight in the sub-shot data c is c1, and the sub-lens data d The target frame with the largest frame weight is d1, the target frame with the largest frame weight in the sub-shot data e is e1, and the target frame with the largest frame weight in the sub-shot data f is f1. That is, the target frames corresponding to users 1 to 200 are a1, b1, c1, and d1 (N=4); the target frames corresponding to users 201 to 600 are c1, d1, e1, and f1 (N=4); 601 to 1000 The target frames corresponding to the number user are a1, b1, e1, and f1 (N=4).

The generating device classifies all users whose target frames (M=N=4) are the same into the same class, that is, users of numbers 1 to 200 are classified as class A. Users from 201 to 600 are classified as Class B. Users from 601 to 1000 are classified as Class C.

The generating device divides the same type of users into four groups randomly, and performs a comparison experiment test on the pictures corresponding to the four identical target frames shared by the users of the four groups.

Specifically, for the class A user, the generating device divides the users 1 to 50 into a group, and records them as the A1 group; divides the users 51 to 100 into a group, and records them as the A2 group; and divides the users from 101 to 150 into the group. One group is recorded as A3 group; the users from 151 to 200 are grouped into one group and recorded as A4 group. Then, the generating device allows the A1 group to test the picture corresponding to a1, and let the A2 group test the picture corresponding to b1, let the A3 group test the picture corresponding to c1, and let the A4 group test the picture corresponding to d1. Finally, the click rate of each picture is counted, the picture corresponding to a1 is 70%, the picture corresponding to b1 is 80%, the picture corresponding to c1 is 75%, and the picture corresponding to d1 is 95%, then the picture corresponding to d1 is generated by the device. (ie the target picture) as an advertisement picture for the class A user.

For Class B users: Users from 201 to 300 are grouped as B1 group, users from 301 to 400 are grouped, recorded as B2 group, and users from 401 to 500 are grouped as B3 group, 501 to 600. The number of users is a group, which is recorded as B4 group. Then, the generating device allows the B1 group to test the picture corresponding to c1, and let B2 test the picture corresponding to d1, let B3 test the picture corresponding to e1, and let B4 test the picture corresponding to f1. Finally, the click rate of each picture is counted. The picture corresponding to c1 is 85%, the picture corresponding to d1 is 85%, the picture corresponding to e1 is 88%, and the picture corresponding to f1 is 90%. The picture corresponding to f1 is set as the advertisement picture of the class B user.

For Class C users: 601 to 700 users are a group, recorded as C1 group, 701 to 800 users are grouped, recorded as C2 group, 801 to 900 users are grouped, recorded as C3 group, 901 to 1000 The number of users is a group and is recorded as the C4 group. Then, the generating device allows C1 to test the picture corresponding to a1, and C2 tests the picture corresponding to b1, so that C3 tests the picture corresponding to e1, and allows C4 to test the picture corresponding to f1. Finally, the click rate of each picture is counted, the picture corresponding to a1 is 65%, the picture corresponding to b1 is 78%, the picture corresponding to c1 is 66%, the picture corresponding to e1 is 63%, and the picture corresponding to f1 is 62%. Then, the generating device uses the picture corresponding to b1 as the advertisement picture of the class C user.

The generating device presets an update rule: the advertisement picture is updated every two episodes of the update of the TV show. A week later, the TV series "Da Jang Geum" updated two episodes. The system entered the third and fourth episodes of "Da Jang Geum", and the generating device updates various users according to the newly input third episode video and fourth episode video. Corresponding ad image.

The method for generating the information display picture in the embodiment of the present invention is described above. The following describes the device for generating the information display picture in the embodiment of the present invention. Referring to FIG. 4, an implementation of the information display picture generating device in the embodiment of the present invention is described. Examples include:

a segmentation module 401, configured to divide a target video determined by the terminal into a plurality of video frames;

The first determining module 402 is configured to determine, according to user characteristics, N target frames corresponding to each user, where the target frame belongs to a video frame, and N is an integer greater than 1.

a second determining module 403, configured to determine a user having M identical target frames as a similar user, where M is an integer, and 1<M≤N;

The test module 404 is configured to divide the similar users determined by the second determining module into M groups, and perform a comparison experiment test on the pictures corresponding to the M identical target frames by the users of the M group;

The third determining module 405 is configured to determine, according to the result of the comparison experiment test, the target picture with the highest click rate CTR in the pictures corresponding to the M identical target frames, and display the target picture as the information of the same user.

The segmentation module 401 of the embodiment of the present invention may divide the target video into a plurality of video frames, the first determining module 402 determines N target frames corresponding to each user according to the user characteristics, and the second determining module 403 will have M identical target frames. The user is determined to be the same type of user, and the test module 404 divides the user into the M group for each type of user, and uses the user of the M group as the test user, and performs the image corresponding to the M target frames shared by the user. Control experiment test, third determination module 405 according to the control The experimental test results determine one or more target images with the highest click-through rate, and display the one or more target images as information for such users. It can be seen that the solution can automatically generate information display pictures, and can classify users according to user characteristics, generate different information display pictures for different categories of users, and display different information according to user characteristics to different categories of users, which is more targeted. Improve image clicks, provide effective information to more users, and save manpower.

Based on the embodiment corresponding to FIG. 4, referring to FIG. 5, in another embodiment of the device for generating information display pictures provided by the embodiment of the present invention, the segmentation module 401 may include:

a first dividing unit 4011, configured to divide the target video into a plurality of lens data;

a second dividing unit 4012, configured to divide each lens data into a plurality of sub-lens data;

The third dividing unit 4013 is configured to divide each sub-lens data into a plurality of video frames.

The embodiment of the invention provides a specific manner of segmenting the target video, and improves the achievability of the solution.

Based on the embodiment corresponding to FIG. 5, referring to FIG. 6, in another embodiment of the apparatus for generating information display pictures provided by the embodiment of the present invention, the first determining module 402 includes:

a first determining unit 4021, configured to determine L sub-shot data corresponding to each user according to user characteristics, where L is an integer equal to or greater than 1;

The second determining unit 4022 determines a target frame corresponding to each sub-shot data in the L sub-shot data according to the preset frame weight.

The embodiment of the invention provides a specific implementation manner for determining a target frame, and improves the achievability of the solution.

Based on the embodiment corresponding to FIG. 6 above, referring to FIG. 7, in another embodiment of the apparatus for generating information display pictures provided by the embodiment of the present invention, the first determining unit 4021 includes:

a first determining sub-unit 40211, configured to determine, for each user, target sub-shot data including a tag information corresponding to the user among the plurality of sub-lens data corresponding to the target video;

The second determining sub-unit 40212 is configured to determine L pieces of sub-shot data of the preset sub-lens weights in the target sub-shot data.

In the embodiment of the present invention, the information display picture generating device provides a method for determining L sub-shot data corresponding to each user, thereby improving the achievability of the solution.

Based on the embodiment corresponding to FIG. 6 or FIG. 7 , referring to FIG. 8 , in another embodiment of the information display picture generating apparatus provided by the embodiment of the present invention, the information display picture generating apparatus further includes include:

a dividing module 406, configured to divide the video frames in the sub-shot data into K classes by K-means clustering for each sub-shot data;

a fourth determining module 407, configured to determine, in each type of video frame, a video frame that is closest to a cluster center as a key frame of the video frame;

a fifth determining module 408, configured to determine, according to the frame parameter, a frame weight corresponding to each key frame;

The second determining unit 4022 includes:

The third determining sub-unit 40221 is configured to determine, for the L sub-shot data, a target frame with the largest frame weight among the key frames included in the sub-shot data.

The embodiment of the invention provides a specific manner for determining a target frame in the L sub-shot data, and improves the achievability of the solution.

In another embodiment of the device for generating an information display image according to the embodiment of the present invention, the first segmentation unit may include:

The first dividing subunit is configured to divide the target video into a plurality of lens data according to the distance of the color space.

The embodiment of the invention provides a method for dividing a target video into lens data, which improves the achievability of the solution.

In another embodiment of the device for generating an information display image according to the embodiment of the present invention, the second segmentation unit may include:

The second dividing sub-unit is configured to divide each lens data into a plurality of sub-lens data according to a camera moving direction.

The embodiment of the invention provides a method for dividing lens data into sub-lens data, which improves the achievability of the solution.

In a further embodiment of the device for generating an information display image according to the embodiment of the present invention, the third determining module may include:

a third determining unit, configured to determine, according to a result of the comparison experiment test, a plurality of target pictures with the highest CTR in the pictures corresponding to the M identical target frames;

a processing unit that renders and types a plurality of target images;

The fourth determining unit is configured to display the plurality of target pictures after rendering and layout as information of the same type of users.

In the embodiment of the present invention, the third determining module may select multiple target images, and render and format the multiple images to form an information display image, thereby improving the flexibility of the solution.

In another embodiment of the apparatus for generating an information display image according to the embodiment of the present invention, the apparatus for generating an information display image may further include:

An update module for updating the information display image according to a preset rule.

In the embodiment of the present invention, the information display image generating device may further update the information display image according to the preset rule, thereby improving the flexibility of the solution.

The device for generating information display pictures in the embodiment of the present invention is described above from the perspective of a function module. The device for generating information display pictures in the embodiment of the present invention is introduced from the perspective of a hardware entity. Please refer to FIG. 9 and FIG. A schematic diagram of the structure of the information display picture generating device 50 in the embodiment of the invention. The information display device generating device 50 may include an input device 510, an output device 520, a processor 530, and a memory 540. The output device in the embodiment of the present invention may be a display device.

Memory 540 can include read only memory and random access memory and provides instructions and data to processor 530. A portion of the memory 540 may also include a non-volatile random access memory (English name: Non-Volatile Random Access Memory, English abbreviation: NVRAM).

Memory 540 stores the following elements, executable modules or data structures, or subsets thereof, or their extended sets:

Operation instructions: include various operation instructions for implementing various operations.

Operating system: Includes a variety of system programs for implementing various basic services and handling hardware-based tasks.

In the embodiment of the present invention, the processor 530 is configured to:

Dividing the target video determined by the terminal into a plurality of video frames;

Determining N target frames corresponding to each user according to user characteristics, the target frame belongs to a video frame, and N is an integer greater than 1.

Determining a user having M identical target frames as a homogeneous user, M is an integer, and 1 < M ≤ N;

The same type of users are divided into M groups, and the users corresponding to the M target frames are tested by the M group of users;

According to the result of the comparison experiment test, it is determined that the M corresponding frames of the same target frame are clicked through Rate the target image with the highest CTR, and display the target image as the information of this similar user.

The processor 530 controls the operation of the information display device 50. The processor 530 may also be referred to as a central processing unit (English full name: Central Processing Unit: CPU). Memory 540 can include read only memory and random access memory and provides instructions and data to processor 530. A portion of the memory 540 may also include an NVRAM. In a specific application, the components of the information display image generating device 50 are coupled together by a bus system 550. The bus system 550 may include a power bus, a control bus, a status signal bus, and the like in addition to the data bus. However, for clarity of description, various buses are labeled as bus system 550 in the figure.

The method disclosed in the foregoing embodiments of the present invention may be applied to the processor 530 or implemented by the processor 530. Processor 530 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the foregoing method may be completed by an integrated logic circuit of hardware in the processor 530 or an instruction in a form of software. The processor 530 may be a general-purpose processor, a digital signal processor (English name: Digital Signal Processing, English abbreviation: DSP), an application specific integrated circuit (English name: Application Specific Integrated Circuit, English abbreviation: ASIC), ready-made programmable Gate array (English name: Field-Programmable Gate Array, English abbreviation: FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The methods, steps, and logical block diagrams disclosed in the embodiments of the present invention may be implemented or carried out. The general purpose processor may be a microprocessor or the processor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present invention may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor. The software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like. The storage medium is located in the memory 540, and the processor 530 reads the information in the memory 540 and performs the steps of the above method in combination with its hardware.

A person skilled in the art can clearly understand that for the convenience and brevity of the description, the specific working process of the system, the device and the unit described above can refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In the several embodiments provided by the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative For example, the division of the unit is only a logical function division, and the actual implementation may have another division manner, for example, multiple units or components may be combined or may be integrated into another system, or some features may be ignored. Or not. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention, which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: a U disk, a mobile hard disk, a read only memory (English full name: Read-Only Memory, English abbreviation: ROM), a random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic A variety of media that can store program code, such as a disc or a disc.

The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to be limiting; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that The technical solutions described in the embodiments are modified, or the equivalents of the technical features are replaced by the equivalents of the technical solutions of the embodiments of the present invention.

Claims

A method for generating an information display picture, the method is applied to a terminal, and the method includes:

Segmenting the target video determined by the terminal into a plurality of video frames;

Determining N target frames corresponding to each user according to user characteristics, where the target frame belongs to the video frame, and the N is an integer greater than 1;

Determining a user having M identical target frames as a homogeneous user, the M being an integer, and 1 < M ≤ N;

Dividing the same type of users into M groups, and performing a comparison experiment test on the pictures corresponding to the M identical target frames by the users of the M group;

Determining, according to the result of the comparison experiment test, a target picture with the highest click-through rate CTR in the picture corresponding to the M identical target frames, and displaying the picture as the information of the same-type user.
The method of claim 1, wherein the dividing the target video determined by the terminal into a plurality of video frames comprises:

Segmenting the target video into a plurality of shot data;

Dividing each lens data into a plurality of sub-shot data;

Each sub-lens data is segmented into a number of video frames.
The method of claim 2, wherein the determining the N target frames corresponding to each user according to the user characteristics comprises:

Determining L sub-shot data corresponding to each user according to the user feature, where L is an integer equal to or greater than 1;

Determining a target frame corresponding to each sub-shot data of the L sub-shot data according to a preset frame weight.
The method of claim 3, wherein the determining the L sub-shot data corresponding to each user according to the user feature comprises:

Determining, in each of the plurality of sub-lens data corresponding to the target video, target sub-lens data including tag information corresponding to the user;

Determining the top L sub-shot data of the preset sub-lens weights in the target sub-shot data.
The method of claim 3, wherein the method further comprises: after the dividing the target video into a plurality of video frames and before determining the N target frames corresponding to each user according to the user characteristics, the method further comprising:

For each sub-shot data, the video frames in the sub-shot data are divided into K classes by K-means clustering;

Determining the video frame closest to the cluster center in each type of video frame as a key frame of the video frame of the type;

The frame weight corresponding to each key frame is determined according to the frame parameters.
The method according to claim 5, wherein the determining, according to the preset frame weight, the target frame corresponding to each of the L sub-shot data comprises:

For the L sub-shot data, the target frame with the largest frame weight among the key frames included in the sub-shot data is determined.
The method of claim 5 wherein the frame parameters comprise a face ratio or a camera motion direction.
The method according to any one of claims 2 to 7, wherein the dividing the target video into a plurality of shot data comprises:

The target video is segmented into a plurality of shot data according to the distance of the color space.
The method according to any one of claims 2 to 7, wherein the dividing each shot data into a plurality of sub-shot data comprises:

Each lens data is divided into several sub-lens data in the direction of camera motion.
The method according to any one of claims 1 to 7, wherein the determining, according to the result of the comparison experiment test, a target picture with the highest click rate CTR in the pictures corresponding to the M identical target frames, and The target picture as the information display image of the same type of user includes:

Determining, according to the result of the comparison experiment test, a plurality of target pictures having the highest CTR among the pictures corresponding to the M identical target frames;

Rendering and formatting the plurality of target images;

The plurality of target pictures after the rendering and layout are displayed as information of the same type of users.
A device for generating information display pictures, comprising:

a segmentation module, configured to divide the target video determined by the terminal into a plurality of video frames;

a first determining module, configured to determine, according to user characteristics, N target frames corresponding to each user, where the target frame belongs to the video frame, and the N is an integer greater than one;

a second determining module, configured to determine a user having M identical target frames as a user of the same type, where M is an integer, and 1 < M ≤ N;

a test module, configured to divide the similar users determined by the second determining module into M groups, and pass the same The user of the M group performs a comparison experiment test on the pictures corresponding to the M identical target frames;

a third determining module, configured to determine, according to the result of the comparison experiment test, a target picture with the highest click-through rate CTR in the picture corresponding to the M identical target frames, and display the target picture as the information of the same-type user image.
The apparatus of claim 11 wherein said segmentation module comprises:

a first dividing unit, configured to divide the target video into a plurality of lens data;

a second dividing unit, configured to divide each lens data into a plurality of sub-shot data;

And a third dividing unit, configured to divide each sub-lens data into a plurality of video frames.
The apparatus of claim 12, wherein the first determining module comprises:

a first determining unit, configured to determine L sub-shot data corresponding to each user according to user characteristics, where L is an integer equal to or greater than 1;

The second determining unit determines, according to the preset frame weight, a target frame corresponding to each of the L sub-shot data.
The apparatus of claim 13, wherein the first determining unit comprises:

a first determining subunit, configured to determine, for each user, target sub-shot data including a tag information corresponding to the user in the plurality of sub-lens data corresponding to the target video;

a second determining subunit, configured to determine the top L sub-shot data of the preset sub-lens weights in the target sub-shot data.
The device of claim 13 wherein said device further comprises:

a dividing module, configured to divide the video frames in the sub-shot data into K classes by K-means clustering for each sub-shot data;

a fourth determining module, configured to determine, in each type of video frame, a video frame that is closest to a cluster center as a key frame of the video frame;

And a fifth determining module, configured to determine a frame weight corresponding to each key frame according to the frame parameter.
The apparatus of claim 15, wherein the second determining unit comprises:

And a third determining subunit, configured to determine, for the L sub-shot data, a target frame with the largest frame weight among the key frames included in the sub-shot data.
The apparatus according to any one of claims 12 to 16, wherein the first dividing unit comprises:

a first dividing subunit, configured to divide the target video into several according to a distance of a color space Lens data.
The apparatus according to any one of claims 12 to 16, wherein the second dividing unit comprises:

The second dividing sub-unit is configured to divide each lens data into a plurality of sub-lens data according to a camera moving direction.
The apparatus according to any one of claims 12 to 16, wherein the third determining module comprises:

a third determining unit, configured to determine, according to the result of the comparison experiment test, a plurality of target pictures with the highest CTR in the pictures corresponding to the M identical target frames;

a processing unit, configured to render and type the plurality of target images;

And a fourth determining unit, configured to display the picture by using the plurality of target pictures after the rendering and the typesetting as information of the same type of users.
A computer readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 10.
A terminal, the terminal comprising: a processor, a memory; the processor and the memory communicate via a bus;

The memory is for storing instructions;

The processor is configured to invoke an instruction in the memory to perform the method of any one of claims 1 to 10.