WO2019144838A1

WO2019144838A1 - Method and apparatus for use in acquiring evaluation result information of video

Info

Publication number: WO2019144838A1
Application number: PCT/CN2019/072217
Authority: WO
Inventors: 罗江春; 陈锡岩
Original assignee: 北京一览科技有限公司
Priority date: 2018-01-24
Filing date: 2019-01-17
Publication date: 2019-08-01
Also published as: CN108376147B; CN108376147A

Abstract

A method for use in acquiring evaluation result information of a video, the method comprising the following steps: dividing a video into a plurality of segments (S1); acquiring segment evaluation information corresponding to each segment among the plurality of segments (S2); determining, according to the segment evaluation information corresponding to each segment, evaluation result information of the video (S3). The described method allows evaluations of videos to be more accurate and objective so that a plurality of videos may be ranked more precisely.

Description

Method and device for obtaining evaluation result information of video

Cross-reference to related applications

The present application claims priority to Chinese Patent Application No. 201810068733.7, entitled "A Method and Apparatus for Obtaining Evaluation Result Information for Video," filed on January 24, 2018, the content of which is hereby incorporated by reference. The citations are incorporated here.

Technical field

The present invention relates to the field of computer technologies, and in particular, to a method and apparatus for obtaining evaluation result information of a video.

Background technique

In the prior art, a user can evaluate a video viewed by the user, and the computer device can obtain an overall evaluation corresponding to the video by counting all users' evaluations of one video. However, in the prior art, the evaluation of the video is directly based on the complete video as the evaluation object, both from the perspective of the user and from the perspective of the computer device.

Summary of the invention

It is an object of the present invention to provide a method and apparatus for obtaining evaluation result information of a video.

According to an aspect of the present invention, a method for obtaining evaluation result information of a video is provided, wherein the method comprises the following steps:

Divide the video into multiple segments;

Obtaining segmentation evaluation information corresponding to each of the plurality of segments;

The evaluation result information of the video is determined according to the segmentation evaluation information corresponding to each segment.

According to another aspect of the present invention, there is also provided an apparatus for obtaining evaluation result information of a video, wherein the apparatus comprises:

Means for dividing a video into a plurality of segments;

Means for obtaining segmentation evaluation information corresponding to each of the plurality of segments;

Means for determining evaluation result information of the video according to the segmentation evaluation information corresponding to each segment.

Compared with the prior art, the present invention has the advantage of determining the evaluation of a video by dividing the video into a plurality of segments and obtaining segmentation evaluation information corresponding to each of the plurality of segments. The resulting information makes the evaluation of the video more accurate and objective, and thus can more accurately sort multiple videos.

DRAWINGS

Other features, objects, and advantages of the present invention will become more apparent from the Detailed Description of Description

1 is a schematic flow chart of a method for obtaining evaluation result information of a video according to an embodiment of the present invention;

2 is a schematic flow chart of a method for obtaining evaluation result information of a video according to another embodiment of the present invention;

3 is a schematic structural diagram of an apparatus for obtaining evaluation result information of a video according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an apparatus for obtaining evaluation result information of a video according to another embodiment of the present invention.

The same or similar reference numerals in the drawings denote the same or similar components.

Detailed ways

Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as a process or method depicted as a flowchart. Although the flowcharts describe various operations as a sequential process, many of the operations can be implemented in parallel, concurrently or concurrently. In addition, the order of operations can be rearranged. The process may be terminated when its operation is completed, but may also have additional steps not included in the figures. The processing may correspond to methods, functions, procedures, subroutines, subroutines, and the like.

By "computer device", also referred to as "computer" in the context, is meant an intelligent electronic device that can perform predetermined processing, such as numerical calculations and/or logical calculations, by running a predetermined program or instruction, which can include a processor and The memory is executed by the processor to execute a predetermined processing procedure pre-stored in the memory, or is executed by hardware such as an ASIC, an FPGA, a DSP, or the like, or a combination of the two.

The computer device includes, for example, a user device and a network device. The user equipment includes but is not limited to a PC, a tablet, a smart phone, a PDA, etc.; the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing system. A cloud consisting of a large number of computers or network servers, where cloud computing is a type of distributed computing, a super virtual computer consisting of a cluster of loosely coupled computers. Wherein, the computer device can be operated separately to implement the present invention, and can also access the network and implement the present invention by interacting with other computer devices in the network. The network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.

It should be noted that the user equipment, the network equipment, the network, and the like are merely examples, and other existing or future possible computer equipments, such as those applicable to the present invention, are also included in the scope of the present invention and are cited. The way is included here.

The methods discussed later herein, some of which are illustrated by flowcharts, can be implemented in hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to carry out the necessary tasks can be stored in a machine or computer readable medium, such as a storage medium. The processor(s) can perform the necessary tasks.

The specific structural and functional details disclosed are merely representative and are for the purpose of describing exemplary embodiments of the invention. The present invention may, however, be embodied in many alternative forms and should not be construed as being limited only to the embodiments set forth herein.

It should be understood that although the terms "first," "second," etc. may be used herein to describe the various elements, these elements should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, a first unit could be termed a second unit, and similarly a second unit could be termed a first unit, without departing from the scope of the exemplary embodiments. The term "and/or" used herein includes any and all combinations of one or more of the associated listed items.

The terminology used herein is for the purpose of describing the particular embodiments, The singular forms "a", "an", It is also to be understood that the terms "comprising" and """ Other features, integers, steps, operations, units, components, and/or combinations thereof.

It should also be noted that, in some alternative implementations, the functions/acts noted may occur in a different order than that illustrated in the drawings. For example, two figures shown in succession may in fact be executed substantially concurrently or sometimes in the reverse order, depending on the function/acts involved.

The invention is further described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart diagram of a method for obtaining evaluation result information of a video according to an embodiment of the present invention. The method according to the present embodiment includes step S1, step S2, and step S3.

In step S1, the computer device divides the video into a plurality of segments.

The implementation manner in which the computer device divides the video into multiple segments includes but is not limited to:

1) The computer device divides the video into a plurality of segments according to a predetermined time interval.

For example, the predetermined time interval is 10 s (seconds), the computer device treats the video as a segment every 10 s from the beginning, and when the remaining segment is less than 10 s, the remaining segment is taken as a segment.

2) The computer device divides the video into a plurality of segments according to interactive operation information during which the user views the video.

The interactive operation information during the viewing of the video by the user includes any information related to an interaction operation between the user and the video during the video viewing, such as an interaction operation performed by each user and an operation content and operation corresponding to each interaction operation. Time, operating frequency, etc. Preferably, the interaction operation includes, but is not limited to, a play-related operation performed by the user on the video (such as fast forward, backward, increase volume, volume reduction, etc.), and a real-time feedback operation performed by the user on the video (eg, like Operation, bad evaluation operation, sharing operation, etc.). Preferably, the evaluation tendency corresponding to the specific interaction operation may be predefined, such as the user's finger sliding to the left on the video to indicate the like, the rightward sliding to indicate dislike, and the user to double-tap the screen to indicate that the user prefers to long-press the screen to exceed the predetermined value to indicate dislike. .

As an example, the duration of a video is 20 minutes, and the computer device counts the interactive operation information of 200 users during the viewing of the video, and the interactive operation information includes the corresponding back and fast forward operations performed by the 200 users. Operating time, the computer device determines, according to the interactive operation information, that 20% of the 200 users perform fast forward operation in the first minute of the video, and 10% of the users are in the fifth to tenth minute of the video. The back operation is performed, and the computer device divides the video into the following four segments according to the interactive operation information: 0-1 minutes, 2 to 4 minutes, 5-10 minutes, 11-20 minutes.

As another example, a live video has a duration of 10 minutes, and the computer device counts interactive operation information of 100 users during viewing of the video, the interactive operation information indicating each click operation performed by each user during viewing of the video. According to the interactive operation information, the computer device determines that 50% of the users like the first to second minutes of the video, and 2% of the users like the third to the last minute of the video, in the 8th to 10th minutes of the video. 60% of the users like it, the computer device divides the video into the following four segments according to the interactive operation information: 0-1 minutes, 1 to 2 minutes, 3-7 minutes, 8-10 minutes.

It should be noted that the present invention finds that the interactive operation of the user during viewing of the video can accurately reflect the user's preference for different segments in the video. For example, when a user prefers a piece of content, he or she performs a back operation to repeatedly view the piece of content or increase the volume to more clearly identify the content of the video, and performs a fast forward operation to filter when a piece of content is less preferred. Drop the content or reduce the volume to reduce the focus. If the user likes the general level, usually do not perform any interactive operations; for example, the user can perform a like or bad review when seeing content that they like or dislike. Express your current feelings in real time. Therefore, the plurality of segments obtained based on the present embodiment 2) can reflect the change in preferences of the user during viewing of the video.

3) Step S1 further includes step S11 and step S12.

In step S11, the computer device obtains video scene information of the video.

The video scene information includes any information related to a video scene in the video. One video scene corresponds to one frame or consecutive multiple frames in the video. Preferably, the video scene information includes, but is not limited to, at least one of the following: the number of video scenes included in the video, the video frame corresponding to each video scene, the number of frames or time length corresponding to each video scene, and each The type of scene corresponding to the video scene (such as food scenes, travel scenes, meeting scenes, etc.).

The computer device can obtain video scene information of the video in various manners.

For example, the computer device directly determines video scene information of the video based on the indication information from the user.

For example, in a database of a computer device, a plurality of specific visual objects and a scene type corresponding to each specific visual object are pre-stored, and when it is determined that a specific visual object appears in one frame of the video, the computer device uses the frame as a video scene. And the scene type corresponding to the specific visual object is used as the scene type of the video scene, whereby the computer device can determine video scene information of the video, where the video scene information is used to indicate each video scene including the specific visual object and Scene type.

As a preferred solution, the computer device performs semantic understanding on the video according to the audio feature information and/or the visual feature information of the video to obtain video scene information of the video.

Wherein, the audio feature information includes any information related to audio features of the video, such as pitch, pitch, timbre, and the like.

Wherein, the visual feature information includes any information related to visual features of the video, such as subtitles of the video, objects (such as characters, articles, etc.) presented in the video.

Specifically, the computer device performs semantic understanding on the video according to the audio feature information and/or the visual feature information of the video to determine the meaning of the video (that is, what the video is expressing), and then obtain the video of the video based on the meaning of the video. Scene information.

As an example, the computer device performs voice recognition on the audio feature information of the video to obtain a text recognition result, and determines, by semantic analysis of the text recognition result, that the video tells a cooking method from beginning to end, and the computer device determines Video scene information of the video, the video scene information is used to indicate that the video as a whole is a video scene, and the video scene is a gourmet scene.

Preferably, the computer device separately performs semantic understanding on each frame of the video according to the audio feature information and/or the visual feature information of the video. When there are consecutive multiple frames with the same meaning or similar, the multi-frame is used as one of the videos. The video scene, and determining the scene type of the video scene based on the meaning of the multi-frame.

As another example, for a frame in the video, the computer device obtains visual feature information of the frame, where the visual feature information indicates that the object presented in the frame includes: a character, a backpack, and a tent; then the computer device performs the visual feature information according to the Semantic understanding, determining that the character in the frame is traveling; when determining that the continuous multi-frame in the video means that the character is traveling, the computer device regards the multi-frame as a video scene in the video, and determines the video The scene is a tourist scene. Similarly, a computer device can determine other video scenes in the video as well as its scene type.

It should be noted that the above examples are only for better explaining the technical solutions of the present invention, and are not limited to the present invention. Those skilled in the art should understand that any implementation manner of obtaining video scene information of the video should be included in Within the scope of the invention.

In step S12, the computer device divides the video into a plurality of segments according to the video scene information.

As an example, the video scene information of the video includes the scene type corresponding to each frame of the video, and the computer device treats the continuous multi-frame as a segment whenever the scene types corresponding to the consecutive multiple frames of the video are the same. The video is divided into multiple segments. In this example, each segment of the video corresponds to one scene type, and the scene types corresponding to the two adjacent segments are different.

As a preferred solution of step S12, when it is determined that at least two consecutive video scenes in the video are the same or associated according to the video scene information, the computer device determines the video segment corresponding to the at least two video scenes as A segment of the video.

Preferably, the computer device determines whether the two video scenes are associated based on the degree of association of the scene type corresponding to the video scene. Preferably, the association relationship between the plurality of scene types may be pre-stored in the computer device.

As an example, the video scene information of the video includes a scene type corresponding to each frame of the video, and the computer device determines, according to the video scene information, that the first 0-1 minute of the video is a gourmet scene, and the first tenth minute is a tourist scene, The 10th to 11th minutes are game scenes. Since the food scene is associated with the travel scene, the computer device takes the 0-10 minutes of the video as a segment of the video and the 10th to 11th minute of the video as another video. Segmentation. In this example, each segment of the video corresponds to one scene or corresponds to multiple associated scenes.

It should be noted that the foregoing implementation manners 2) and 3) may be combined. Specifically, the computer device divides the video into multiple segments according to the interaction operation information of the user during viewing of the video and the video scene information of the video. . As an example, the computer device determines, according to the video scene information, that the 0-1th minute of the video is a gourmet scene, the 1-10th minute is a travel scene, and the 10th to 11th minutes are game scenes; the computer device is according to the user viewing The interactive operation information during the video determines that 80% of the users continue to like the 0 to 5 minutes of the video, and the user divides the video into the following three segments: 0 to 5 minutes, 5 to 10 minutes, 10th Until 11 minutes. As another example, one video scene of the video corresponds to consecutive multiple frames in the video. When the interactive operation information indicates that most users perform opposite interaction operations in the video scene, the computer device performs based on the user's interactive operation information. The video scene is divided into two segments.

It should be noted that considering that the beginning and end of a video usually have a piece of content that is not the main content of the video, or is not the content that the user is interested in (such as movie titles and credits), then the content is evaluated. It is not significant, therefore, preferably, part of the content at the beginning and end of the video can be removed, and the operation of step S1 is performed on the video segment remaining after the removal operation to divide the video segment into a plurality of segments. For example, the predetermined duration is 15 s and the total duration of the video is 1 hour. The computer device removes the first 15 s and the ending 15 s of the video, and divides the remaining 59 minutes and 30 video segments into multiple segments based on the above implementation 2). .

It should be noted that the foregoing examples are only for better explaining the technical solutions of the present invention, and are not intended to limit the present invention. Those skilled in the art should understand that any implementation that divides video into multiple segments should be included in Within the scope of the invention.

In step S2, the computer device obtains segmentation evaluation information corresponding to each of the plurality of segments.

Specifically, for each segment in the video, the computer device obtains segmentation evaluation information corresponding to the segment. Wherein, for each of the plurality of users, the computer device may first determine the segmentation evaluation information of the segment corresponding to the user; and then, the computer device according to the segmentation evaluation information of the segment corresponding to each user, The segmentation evaluation information of the segment corresponding to the plurality of users is determined.

Wherein the segmentation evaluation information includes any information indicating an evaluation for the segment. Preferably, the segmentation evaluation information may be an evaluation score (such as a value in the evaluation score of 0 to 100, the higher the evaluation score is, the higher the evaluation) or the evaluation level (such as the highest rating of the level A, the level B times) Therefore, the rating C is the lowest).

Specifically, the implementation manner in which the computer device obtains the segmentation evaluation information corresponding to each of the plurality of segments includes, but is not limited to:

1) For each segment, the computer device determines the segmentation evaluation information corresponding to the segment according to the vital information of the user during viewing of the segment.

Wherein the vital sign information includes any information related to the physical characteristics of the user. Preferably, the vital sign information includes, but is not limited to, a user's body temperature change, a blood pressure/heart rate change, an eye movement condition, a pupil state, a body motion, a face change, and the like. Preferably, the sign of the change of the sign includes a change in the sign of the user during viewing of the segment compared to when viewing the previous segment.

Among them, the computer device can obtain the physical sign information of the user in various ways. For example, during a user watching a video, the computer device performs real-time monitoring through its internally mounted camera to obtain vital sign information for use. For another example, during a user watching a video, the computer device is connected to the wearable device worn by the user and receives the physical sign information of the user from the wearable device in real time.

Wherein, each body feature may have a corresponding evaluation rule. For example, if the heart rate of the user increases during viewing of the segment, the evaluation value of the segment is higher; if the heart rate remains unchanged during the viewing of the segment, the evaluation value of the segment is lower. For another example, if the user nods or laughs, the evaluation value of the segment is higher; if the user keeps shaking his head, the evaluation value of the segment is lower.

2) For each segment, the computer device determines the segmentation evaluation information corresponding to the segment according to the interaction operation information of the user during viewing of the segment.

Wherein, the interactive operation information of the user during viewing of the segment includes any information related to the interaction operation between the user and the segment. The interactive operation information of the user during viewing of the segment is similar to the interaction operation information of the user during the viewing of the video, and details are not described herein again.

As an example, if the user's interactive operation information during viewing of a segment indicates that the user performs a continuous like operation during viewing of the segment, the segment corresponds to a higher rating level if the user is viewing a segment. The interactive operation information indicates that the user performs a fast forward operation during viewing of the segment, and the corresponding evaluation level of the segment is lower.

3) For each segment, the computer device determines segmentation evaluation information corresponding to the segment according to the segmentation play record information.

The segmented play record information includes any information related to the segmented history play record. Preferably, the segmented play record information includes the number of times the segment is played, the ratio of being played repeatedly, the ratio of being completely played, and the proportion of being played back.

As an example, the correspondence between the ratio in which the segment is completely played back and the evaluation level is stored in the computer device as follows: the scale range (0, 40%) corresponds to the level C, and the scale range (41%, 70%) corresponds to the level. B, the scale range (71%, 100%) corresponds to level A; in step S1, the video is divided into the following three segments: section1, section2, section3; in step S2, the computer device is based on the above three segments Playing the record information and determining that the proportions of section1, section2, and section3 are completely played are: 60%, 50%, 95%, respectively, the computer device determines that the evaluation level of section1 and section2 is B according to the object relationship, and the evaluation level of section3 is A.

It should be noted that the implementations 1), 2), and 3) of the above step S2 may be combined. For example, for each of the segments, the computer device determines the segmentation evaluation information corresponding to the segment based on the vital information and the interactive operation information of the user during viewing of the segment. For another example, for each segment, the computer device determines the segmentation evaluation information corresponding to the segment according to the vital information of the user during viewing of the segment and the play record information of the segment. For another example, for each segment, the computer device determines the segmentation evaluation information corresponding to the segment according to the interaction operation information of the user during viewing of the segment and the play record information of the segment. For another example, the computer device determines the segmentation evaluation information corresponding to the segment according to the physical information and the interactive operation information during the viewing of the segment, and the play record information of the segment.

It should be noted that the above examples are only for better explaining the technical solutions of the present invention, and are not intended to limit the present invention. Those skilled in the art should understand that any one of the plurality of segments is obtained. The implementation of the segmentation evaluation information should be included in the scope of the present invention.

In step S3, the computer device determines the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment.

Wherein, the evaluation result information includes any information for indicating an evaluation result for the video. Preferably, similar to the segmentation evaluation information, the evaluation result information may also be an evaluation score or an evaluation rating.

The computer device can determine the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment in a plurality of manners.

For example, the computer device determines the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment, and based on the following formula:

P=(T ₁ P ₁ +T ₂ P ₂ +...T _n P _n )/T

Where P denotes the evaluation result information of the video, T _i denotes the length of time of the i-th segment, P _i denotes the evaluation score of the i-th segment, i=1, 2...n, n is the number of segments, T is the total length of time of the video.

For another example, the predefined evaluation level is A, B, and C from high to low; in step S1, the computer device divides the video into three segments; in step S2, the computer device obtains the corresponding three segments. The evaluation levels are: A, C, and C respectively; in step S3, the computer device quantizes the evaluation level of each segment, and determines that the evaluation level corresponding to the video is B.

Preferably, the computer device can further determine the evaluation result information of the video in combination with the playback record information of the video.

The play record information of the video includes any information related to the history play record of the video. Preferably, the play record information of the video includes the number of times the video is played, the ratio of being played repeatedly, the proportion of being completely played, and the proportion of being played back.

As an example, the computer device first determines the preliminary evaluation result information of the video according to the segmentation evaluation information corresponding to each segment, and then, based on the above formula, the computer device combines the playback evaluation information of the video with the initial evaluation information. Adjusting (such as when the proportion of the video being fully played is greater than the first predetermined threshold, increasing the evaluation level of the video or increasing the evaluation score of the video, when the proportion of the video being completely played is less than the second predetermined threshold, reducing the evaluation level of the video or Reduce the evaluation score of the video) to determine the final evaluation result information of the video.

As a preferred solution, the solution of this embodiment further includes the following steps: the computer device obtains weight information of each segment. The step S3 further includes: determining, by the computer device, the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment, and combining the weight information of each segment. The preferred embodiment will be described in detail in subsequent embodiments, and details are not described herein again.

It should be noted that the above examples are only for better explaining the technical solutions of the present invention, and are not limited to the present invention. Those skilled in the art should understand that any segmentation evaluation information corresponding to each segment is determined. The implementation of the evaluation result information of the video should be included in the scope of the present invention.

As a preferred solution, the method of this embodiment further includes the step of the computer device sorting the plurality of videos according to the evaluation result information of each of the plurality of videos.

Preferably, if the computer device does not consider the play record information of the video when determining the evaluation result information of the video, in the preferred solution, the computer device may combine the video according to the evaluation result information of each of the plurality of videos. Playing record information to sort the plurality of videos. For example, the computer device performs preliminary sorting on the plurality of videos according to the evaluation result information of each of the plurality of videos, and then the computer device adjusts the ordering of the plurality of videos in combination with the play recording information of the video.

It should be noted that when the computer device presents the evaluation result information of the video to the user, the segmentation evaluation information of the video may be presented to the user at the same time. Preferably, the computer device only presents the segmentation evaluation information of the partial segmentation of the video to the user (such as showing the user which segment is the highest evaluated and the evaluation value corresponding to the segment), and more preferably, the computer device also provides the user to the user. The scene type corresponding to the partial segment is presented, so that the user can conveniently and quickly find the video and segment that he wants to watch according to the type of the scene he likes.

In the prior art, a user can evaluate a video viewed by the user, and the computer device can obtain an overall evaluation corresponding to the video by counting all users' evaluations of one video. However, in the prior art, whether from the user's point of view or from the perspective of a computer device, the evaluation of the video is directly based on the complete video as an evaluation object, for example, counting each user's rating on the movie "Transformers 5". Get the overall rating for "Transformers 5".

The present invention recognizes that a user may have different levels of preference or attention to different portions or content in the video, which may cause the user's overall evaluation of the video to be biased or not accurately reflect the user's true perception of the video. For example, although the user likes a piece in the video very much, because the user is extremely disgusted with the other piece, the user only evaluates the video for the other piece, that is, the user's evaluation of the video actually only represents User's evaluation of this other segment. The prior art is not aware of the above problems when evaluating video.

According to the solution of the present embodiment, it is considered that the user may have different degrees of preference or attention to different parts or contents in the video, by dividing the video into a plurality of segments, and obtaining each of the plurality of segments The segmentation evaluation information corresponding to the segment is used to determine the evaluation result information of the video, so that the evaluation of the video is more accurate and objective, and thus the multiple videos can be sorted more accurately.

2 is a schematic flow chart of a method for obtaining evaluation result information of a video according to another embodiment of the present invention. The method according to the present embodiment includes step S1, step S2, step S3, and step S4, wherein the step S3 further includes step S31. The implementation of the step S1 and the step S2 have been described in detail in the embodiment shown in FIG. 1 and will not be further described herein.

In step S4, the computer device obtains weight information for each segment.

Wherein, the segmented weight information includes any information indicating the weight of the segment, such as a weight value or a weight level of the segment (preferably, the weight level can also be quantized into a numerical value) and the like.

Specifically, the implementation manner in which the computer device obtains the weight information of each segment includes, but is not limited to:

1) The computer device determines the weight information of each segment according to the type of the scene corresponding to each segment.

For example, the weight information corresponding to the different scene types is set in advance. For each segment of the video, the computer device obtains the scene type corresponding to the segment according to the video scene information of the video, and the weight information corresponding to the scene type. As the weight information of the segment.

For another example, for each segment of the video, the computer device obtains the scenario type corresponding to the segment according to the video scene information of the video, and determines the weight information of the segment according to the degree of correlation between the scenario type and the video topic. The higher the degree of correlation corresponding to the segment, the greater the weight of the segment.

2) For each of the segments, the computer device determines weight information for the segment based on the presentation feature information of the particular visual object of the video in the segment.

It should be noted that the specific visual object is preferably a visual object with a higher degree of relevance to the video theme, such as using a plurality of protagonists in the video as specific visual objects.

Wherein the presentation feature information includes any information related to the presentation features of the particular visual object in the segment. Preferably, the presentation feature information includes, but is not limited to, the number of presentations of the specific visual object in the segment, the length of the presentation, and the like, wherein the more the specific visual object is presented in the segment, the weight of the segment The higher the length of time that a particular visual object is rendered in a segment, the higher the weight of that segment.

As an example, the predetermined condition is as follows: when the ratio of the length of time that a particular visual object is presented in the segment to the length of the segment exceeds 1/2, the weighting level of the segment is A; when the ratio is lower than When 1/2 is higher than 1/5, the weight of the segment is B; when the ratio is lower than 1/5, the weight of the segment is C; the specific visual object corresponding to a movie is the character A; In step S1, the computer device divides the movie into three segments; in step S4, the computer device determines, according to the presentation feature information of the person A in the three segments, that the character A is presented in the three segments. The ratio between the length of time and the length of the segment is: 4/40, 10/40, 25/40, respectively, and the computer device determines, according to the predetermined condition, that the weights of the three segments are: C, B, A.

Preferably, for each segment, the computer device determines the segment according to the presentation feature information of the specific visual object of the video in the segment and the presence feature information of the specific visual object in the other segment. Weight information.

As an example, a specific visual object corresponding to a movie is a character A; in step S1, the computer device divides the movie into three segments; in step S4, the computer device respectively obtains the character A in the three segments. The length of time: 4 minutes, 6 minutes, 10 minutes, the computer device determines the weight values of the three segments based on the ratio of the length of time presented by the character A in the three segments (ie 4:6:10) It is: 0.2, 0.3, 0.5.

It should be noted that the foregoing implementation manners 1) and 2) may be combined. For example, for each segment of the video, the computer device according to the type of the scene corresponding to the segment and the presentation feature of the specific visual object in the segment. Information, determining the weight information of the segment.

It should be noted that the above examples are only for better explaining the technical solutions of the present invention, and are not limited to the present invention. Those skilled in the art should understand any implementation manner of obtaining the weight information of each segment (for example, It is within the scope of the present invention to determine the weight information of the segment based on the degree of correlation between the meaning of the segmentation and the video subject.

In step S31, the computer device determines the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment and the weight information of each segment.

P=(T ₁ P ₁ W ₁ +T ₂ P ₂ W ₂ +...T _n P _n W _n )/T(W ₁ +W ₂ +...W _n )

Wherein P represents the evaluation result information of the video, T _i represents the length of time of the i-th segment, P _i represents the evaluation score of the i-th segment, and W _i represents the weight value of the i-th segment, i=1 , 2...n, n is the number of segments, and T is the total length of time of the video.

Preferably, the computer device may further determine the evaluation result information of the video according to the segmentation evaluation information and the weight information corresponding to each segment.

It should be noted that the above examples are only for better explaining the technical solutions of the present invention, and are not intended to limit the present invention. Those skilled in the art should understand that any segmentation evaluation information corresponding to each segment is Combining the weight information of each segment, determining the implementation manner of the evaluation result information of the video should be included in the scope of the present invention.

According to the solution of the embodiment, according to the segmentation evaluation information corresponding to each segment, and combining the weight information of each segment, the evaluation result information of the video is determined, thereby further improving the evaluation result of the video. The accuracy of the information.

FIG. 3 is a schematic structural diagram of an apparatus for obtaining evaluation result information of a video according to an embodiment of the present invention. The apparatus for obtaining the evaluation result information of the video (hereinafter simply referred to as "evaluation apparatus") according to the present embodiment includes the first division means 1, the first obtaining means 2, and the first determining means 3.

The first dividing means 1 is for dividing the video into a plurality of segments.

The implementation manner of dividing the video into multiple segments by the first dividing device 1 includes but is not limited to:

1) The first dividing means 1 divides the video into a plurality of segments according to a predetermined time interval.

For example, the predetermined time interval is 10 s (seconds), the first dividing device 1 takes the video as a segment every 10 s from the start point, and when the remaining segment is less than 10 s, the remaining segment is taken as one segment.

2) The first dividing means 1 further comprises a second dividing means (not shown). The second dividing means is configured to divide the video into a plurality of segments according to interactive operation information during a user viewing the video.

As an example, the duration of one video is 20 minutes, and the second dividing device counts the interactive operation information of 200 users during the viewing of the video, and the interactive operation information includes each back and fast forward operation performed by the 200 users. Corresponding operation time, the second dividing device determines, according to the interactive operation information, that 20% of the 200 users perform fast forward operation in the first minute of the video, and 10% of the users are in the fifth minute of the video The back-off operation is performed between the 10th minutes, and the second dividing means divides the video into the following four segments according to the interactive operation information: 0-1 minutes, 2 to 4 minutes, 5-10 minutes, 11-20 minutes.

As another example, a live video has a duration of 10 minutes, and the second dividing device counts interactive operation information of 100 users during viewing of the video, the interactive operation information indicating each time the user performs during the viewing of the video. According to the interactive operation information, the second dividing device determines that 50% of the users like the first to the second minute of the video, and 2% of the users like the third to the last minute of the video, in the eighth of the video. 60% of users like it in 10 minutes, the second dividing device divides the video into the following four segments according to the interactive operation information: 0-1 minute, 1 to 2 minutes, 3-7 minutes, 8-10 minutes .

3) The first dividing device 1 further includes a third obtaining device (not shown) and a third dividing device (not shown).

The third obtaining means is configured to obtain video scene information of the video.

The third obtaining device can obtain video scene information of the video in various manners.

For example, the third obtaining means determines the video scene information of the video directly according to the indication information from the user.

For example, in the database of the computer device, a plurality of specific visual objects and a scene type corresponding to each specific visual object are pre-stored, and when it is determined that a specific visual object appears in one frame of the video, the third obtaining device regards the frame as a a video scene, and the scene type corresponding to the specific visual object is used as the scene type of the video scene, whereby the third obtaining means may determine video scene information of the video, where the video scene information is used to indicate each of the specific visual objects Video scene and its scene type.

As a preferred solution, the third obtaining device performs semantic understanding on the video according to the audio feature information and/or the visual feature information of the video to obtain video scene information of the video.

The visual feature information includes any information related to visual features of the video, such as subtitles of the video, objects (such as characters, articles, etc.) presented in the video.

Specifically, the third obtaining device performs semantic understanding on the video according to the audio feature information and/or the visual feature information of the video to determine the meaning of the video (that is, what the video is expressing), and then obtain the video based on the meaning of the video. Video scene information.

As an example, the third obtaining device performs voice recognition on the audio feature information of the video to obtain a text recognition result, and determines, by semantic analysis of the text recognition result, that the video tells a cooking method from the beginning to the end, The third obtaining device determines video scene information of the video, where the video scene information is used to indicate that the video as a whole is a video scene, and the video scene is a gourmet scene.

Preferably, the third obtaining means separately performs semantic understanding on each frame of the video according to the audio feature information and/or the visual feature information of the video, and when there are consecutive multiple frames having the same meaning or similar, the multi-frame is used as the video. a video scene, and determining a scene type of the video scene based on the meaning of the multi-frame.

As another example, for one frame in the video, the third obtaining device obtains visual feature information of the frame, where the visual feature information indicates that the object presented in the frame includes: a character, a backpack, a tent; The visual feature information is semantically understood to determine that the character in the frame is traveling; then when it is determined that the continuous multi-frame in the video means that the character is traveling, the third obtaining device uses the multi-frame as a video in the video. Scene and determine the video scene as a tourist scene. Similarly, the third obtaining means can determine other video scenes in the video and their scene types.

The third dividing device is configured to divide the video into a plurality of segments according to the video scene information.

As an example, the video scene information of the video includes the scene type corresponding to each frame of the video, and the third dividing device uses the continuous multi-frame as a segment whenever the scene types corresponding to the consecutive multiple frames of the video are the same. Thereby dividing the video into multiple segments. In this example, each segment of the video corresponds to one scene type, and the scene types corresponding to the two adjacent segments are different.

As a preferred solution, the third dividing means further comprises a fourth dividing means (not shown). The fourth dividing device is configured to determine, according to the video scene information, that at least two consecutive video scenes in the video are identical or related, determining a video segment corresponding to the at least two video scenes as a segment of the video .

Preferably, the fourth dividing device may determine whether the two video scenes are associated based on the degree of association of the scene type corresponding to the video scene. Preferably, the association relationship between the plurality of scene types may be pre-stored in the computer device.

As an example, the video scene information of the video includes a scene type corresponding to each frame of the video, and the fourth dividing device determines, according to the video scene information, that the 0-1th minute of the video is a gourmet scene, and the first 1-10 minutes is a tour. Scenes, 10th to 11th minutes are game scenes. Since the food scene is associated with the tourist scene, the fourth dividing device takes the 0-10 minutes of the video as a segment of the video and the 10th to 11th minutes of the video as Another segment of the video. In this example, each segment of the video corresponds to one scene or corresponds to multiple associated scenes.

It should be noted that the foregoing implementation manners 2) and 3) may be combined. Specifically, the first dividing device 1 divides the video into multiples according to the interactive operation information of the user during viewing of the video and the video scene information of the video. Segmentation. As an example, the first dividing device 1 determines, according to the video scene information, that the 0-1th minute of the video is a gourmet scene, the 1-10th minute is a tourist scene, and the 10th to 11th minutes are game scenes; the first dividing device 1 According to the interactive operation information during the viewing of the video by the user, it is determined that 80% of the users continue to like the 0 to 5 minutes of the video, and the user divides the video into the following three segments: 0 to 5 minutes, 5th Up to 10 minutes, 10 to 11 minutes. As another example, one video scene of the video corresponds to consecutive multiple frames in the video. When the interactive operation information indicates that most users perform opposite interaction operations in the video scene, the first dividing device 1 is based on the user's interaction operation. Information is used to divide the video scene into two segments.

It should be noted that considering that the beginning and end of a video usually have a piece of content that is not the main content of the video, or is not the content that the user is interested in (such as movie titles and credits), then the content is evaluated. The meaning is not significant, therefore, preferably, the first dividing device 1 can remove part of the content at the beginning and the end of the video, and perform an operation on the video segment remaining after the removing operation to divide the video segment into a plurality of segments. . For example, the predetermined duration is 15 s and the total duration of the video is 1 hour. The first dividing device 1 removes the first 15 s and the ending 15 s of the video, and divides the remaining 59 minutes and 30 video segments in the video into multiples based on the above implementation 2). Segmentation.

The first obtaining means 2 obtains the segmentation evaluation information corresponding to each of the plurality of segments.

Specifically, for each segment in the video, the first obtaining device 2 obtains segmentation evaluation information corresponding to the segment. Wherein, for each of the plurality of users, the first obtaining means 2 may first determine the segmentation evaluation information of the segment corresponding to the user; after that, the first obtaining device 2 according to the segment corresponding to each user The segmentation evaluation information determines segmentation evaluation information of the segment corresponding to the plurality of users.

Specifically, the implementation manner in which the first obtaining device 2 obtains the segmentation evaluation information corresponding to each of the plurality of segments includes, but is not limited to:

1) The first obtaining means 2 comprises a third determining means (not shown). The third determining means is configured to determine, for each of the segments, the segmentation evaluation information corresponding to the segment according to the vital information of the user during viewing of the segment.

The third determining device can obtain the physical sign information of the user in various manners. For example, during the user watching the video, the third determining device performs real-time monitoring by a camera installed inside the computer device to obtain the vital sign information for use. For another example, during the user watching the video, the computer device is connected to the wearable device worn by the user, and the third determining device receives the vital information of the user from the wearable device in real time.

2) The first obtaining means 2 comprises a fourth determining means (not shown). The fourth determining means is configured to determine, for each segment, the segmentation evaluation information corresponding to the segment according to the interaction operation information during the viewing of the segment by the user.

3) The first obtaining means 2 comprises a fifth determining means (not shown). The fifth determining means is configured to, for each of the segments, the computer device determining the segmentation evaluation information corresponding to the segment according to the segmentation playing record information.

As an example, the correspondence between the ratio in which the segment is completely played back and the evaluation level is stored in the computer device as follows: the scale range (0, 40%) corresponds to the level C, and the scale range (41%, 70%) corresponds to the level. B, the scale range (71%, 100%) corresponds to the rank A; the first dividing device 1 divides the video into the following three segments: section 1, section 2, section 3; and the fifth determining means records the record information according to the above three segments , determining that the proportions of section 1, section 2, and section 3 are completely played: 60%, 50%, 95%, respectively, the fifth determining means determines that the evaluation level of section1 and section2 is B according to the object relationship, and the evaluation level of section3 is A. .

It should be noted that the implementations 1), 2), and 3) of the first obtaining device 2 described above may be combined. For example, for each segment, the first obtaining means 2 determines the segmentation evaluation information corresponding to the segment according to the vital information and the interactive operation information during the viewing of the segment by the user. For another example, for each of the segments, the first obtaining means 2 determines the segmentation evaluation information corresponding to the segment based on the vital information of the user during viewing of the segment and the playback record information of the segment. For another example, for each segment, the first obtaining means 2 determines the segmentation evaluation information corresponding to the segment according to the interactive operation information during the viewing of the segment by the user and the play record information of the segment. For another example, the first obtaining device 2 determines the segmentation evaluation information corresponding to the segment according to the vital information and the interactive operation information during the viewing of the segment, and the play record information of the segment.

The first determining means 3 determines the evaluation result information of the video based on the segmentation evaluation information corresponding to each segment.

The first determining device 3 can determine the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment in a plurality of manners.

For example, the first determining means 3 determines the evaluation result information of the video based on the segmentation evaluation information corresponding to each segment and based on the following formula:

P=(T ₁ P ₁ +T ₂ P ₂ +...T _n P _n )/T

For another example, the predefined evaluation level is A, B, and C from high to low; the first dividing device 1 divides the video into three segments; and the first obtaining device 2 obtains the evaluation levels corresponding to the three segments respectively. : A, C, C; The first determining means 3 quantizes the evaluation level of each segment, and determines that the evaluation level corresponding to the video is B.

Preferably, the first determining means 3 may further determine the evaluation result information of the video in combination with the playing record information of the video.

As an example, the first determining means 3 first determines the preliminary evaluation result information of the video based on the segmentation evaluation information corresponding to each segment, and then, based on the above formula, the first determining means 3 combines the playback record information of the video. The initial evaluation information is adjusted (for example, when the proportion of the video being completely played is greater than the first predetermined threshold, the evaluation level of the video is increased or the evaluation score of the video is increased, when the proportion of the video being completely played is less than the second predetermined threshold, Decrease the evaluation rating of the video or reduce the evaluation score of the video) to determine the final evaluation result information of the video.

As a preferred solution, the evaluation apparatus of the embodiment is further configured to obtain the weight information of each segment, and the first determining apparatus 3 is further configured to use the segmentation evaluation information corresponding to each segment. And combining the weight information of each segment to determine the evaluation result information of the video. The preferred embodiment will be described in detail in subsequent embodiments, and details are not described herein again.

As a preferred embodiment, the evaluation apparatus of the present embodiment further includes a sorting means (not shown). The sorting means is for sorting the plurality of videos based on the evaluation result information of each of the plurality of videos.

Preferably, if the evaluation device does not consider the play record information of the video when determining the evaluation result information of the video, in the preferred embodiment, the sorting device may combine the video according to the evaluation result information of each of the plurality of videos. Playing record information to sort the plurality of videos. For example, the sorting device performs preliminary sorting on the plurality of videos according to the evaluation result information of each of the plurality of videos, and then the sorting device combines the play record information of the video to adjust the order of the plurality of videos.

FIG. 4 is a schematic structural diagram of an apparatus for obtaining evaluation result information of a video according to another embodiment of the present invention. The evaluation device according to the present embodiment includes a first dividing device 1, a first obtaining device 2, a first determining device 3, and a second obtaining device 4, wherein the first determining device 3 further includes a second determining device 31. The implementation manners of the first obtaining device 2 and the first determining device 3 have been described in detail in the embodiment shown in FIG. 3, and details are not described herein again.

The second obtaining means 4 is configured to obtain weight information of each of the segments.

Specifically, the implementation manner in which the second obtaining device 4 obtains the weight information of each segment includes, but is not limited to:

1) The second obtaining means 4 determines the weight information of each of the segments according to the type of the scene corresponding to each segment.

For example, the weight information corresponding to the different scene types is set in advance. For each segment of the video, the second obtaining device 4 obtains the scene type corresponding to the segment according to the video scene information of the video, and corresponding to the scene type. The weight information is used as the weight information of the segment.

For example, for each segment of the video, the second obtaining device 4 obtains the scene type corresponding to the segment according to the video scene information of the video, and determines the segment according to the degree of correlation between the scene type and the video topic. The weight information, wherein the higher the degree of correlation corresponding to the segment, the greater the weight of the segment.

2) The second obtaining means 4 further comprises a sixth determining means (not shown). The sixth determining means is configured to determine, for each of the segments, weight information of the segment according to the presentation feature information of the specific visual object of the video in the segment.

As an example, the predetermined condition is as follows: when the ratio of the length of time that a particular visual object is presented in the segment to the length of the segment exceeds 1/2, the weighting level of the segment is A; when the ratio is lower than When 1/2 is higher than 1/5, the weight of the segment is B; when the ratio is lower than 1/5, the weight of the segment is C; the specific visual object corresponding to a movie is the character A; The first dividing device 1 divides the movie into three segments; the sixth determining device determines, according to the presentation feature information of the person A in the three segments, the length of time that the character A is presented in the three segments and the score The ratios between the segment durations are: 4/40, 10/40, 25/40, respectively, and the sixth determining means determines, according to the predetermined condition, that the weighting levels of the three segments are: C, B, and A, respectively.

Preferably, for each of the segments, the sixth determining means determines, according to the presentation feature information of the specific visual object of the video in the segment, and the presentation feature information of the specific visual object in the other segment. Segmented weight information.

As an example, a specific visual object corresponding to a movie is a character A; the first dividing device 1 divides the movie into three segments; and the sixth determining device respectively obtains the length of time in which the character A in the three segments is presented: 4 Minutes, 6 minutes, and 10 minutes, the sixth determining means determines the weight values of the three segments based on the ratio of the length of time (i.e., 4:6:10) presented by the person A in the three segments: 0.2 , 0.3, 0.5.

It should be noted that the foregoing implementation manners 1) and 2) may be combined. For example, for each segment of the video, the second obtaining device 4 is in the segment according to the type of the scene corresponding to the segment and the specific visual object. Presenting feature information to determine weight information of the segment.

The second determining means 31 determines the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment and the weight information of each segment.

For example, the second determining means 31 determines the evaluation result information of the video based on the segmentation evaluation information corresponding to each segment and based on the following formula:

Preferably, the second determining means 31 may further determine the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment and the weight information, in combination with the play record information of the video.

The present invention provides a user equipment comprising: a memory for storing one or more programs; and one or more processors coupled to the memory when the one or more programs are The method of the present invention for obtaining evaluation result information of a video is executed when the processor executes.

The present invention proposes a computer readable storage medium having stored thereon a computer program, and when the computer program is executed, the method for obtaining evaluation result information of a video of the present invention is executed.

It should be noted that the present invention can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device. In one embodiment, the software program of the present invention may be executed by a processor to implement the steps or functions described above. Likewise, the software program (including related data structures) of the present invention can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like. Additionally, some of the steps or functions of the present invention may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

Additionally, a portion of the invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or solution in accordance with the present invention. The program instructions for invoking the method of the present invention may be stored in a fixed or removable recording medium and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in a The working memory of the computer device in which the program instructions are run. Herein, an embodiment in accordance with the present invention includes a device including a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, triggering The apparatus operates based on the aforementioned methods and/or technical solutions in accordance with various embodiments of the present invention.

It is apparent to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the invention is defined by the appended claims instead All changes in the meaning and scope of equivalent elements are included in the present invention. Any reference signs in the claims should not be construed as limiting the claim. In addition, it is to be understood that the word "comprising" does not exclude other elements or steps. A plurality of units or devices recited in the system claims can also be implemented by a unit or device by software or hardware. The first, second, etc. words are used to denote names and do not denote any particular order.

Claims

A method for obtaining evaluation result information of a video, wherein the method comprises the following steps:

Divide the video into multiple segments;

Obtaining segmentation evaluation information corresponding to each of the plurality of segments;

And determining, according to the segmentation evaluation information corresponding to each segment, the evaluation result information of the video.
The method of claim 1 wherein said step of dividing the video into a plurality of segments comprises:

The video is divided into a plurality of segments according to interactive operation information during which the user views the video.
The method of claim 1 wherein said step of dividing the video into a plurality of segments comprises:

Obtaining video scene information of the video;

The video is divided into a plurality of segments according to the video scene information.
The method according to claim 3, wherein the step of dividing the video into a plurality of segments according to the video scene information comprises:

When it is determined that at least two consecutive video scenes in the video are the same or associated according to the video scene information, the video segments corresponding to the at least two video scenes are determined as one segment of the video.
The method of claim 1, wherein the step of obtaining segmentation evaluation information corresponding to each of the plurality of segments comprises:

For each segment, the segmentation evaluation information corresponding to the segment is determined according to the vital information of the user during viewing of the segment.
The method of claim 1, wherein the step of obtaining segmentation evaluation information corresponding to each of the plurality of segments comprises:

For each segment, the segmentation evaluation information corresponding to the segment is determined according to the interaction operation information of the user during viewing of the segment.
The method of claim 1, wherein the step of obtaining segmentation evaluation information corresponding to each of the plurality of segments comprises:

For each segment, the segmentation evaluation information corresponding to the segment is determined according to the playback record information of the segment.
The method of claim 1 wherein the method further comprises:

Obtaining weight information of each segment;

The step of determining the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment includes:

And determining, according to the segmentation evaluation information corresponding to each segment, and combining the weight information of each segment, the evaluation result information of the video.
The method of claim 8 wherein said step of obtaining weight information for said each segment comprises:

For each of the segments, the weight information of the segment is determined based on the presentation feature information of the particular visual object of the video in the segment.
The method according to any one of claims 1 to 9, wherein the method further comprises:

The plurality of videos are sorted according to evaluation result information of each of the plurality of videos.
An apparatus for obtaining evaluation result information of a video, wherein the apparatus comprises:

Means for dividing a video into a plurality of segments;

Means for obtaining segmentation evaluation information corresponding to each of the plurality of segments;

Means for determining evaluation result information of the video according to the segmentation evaluation information corresponding to each segment.
The apparatus of claim 11, wherein the means for dividing the video into a plurality of segments comprises:

A means for dividing the video into a plurality of segments based on interactive operation information during a user viewing the video.
The apparatus of claim 11, wherein the means for dividing the video into a plurality of segments comprises:

Means for obtaining video scene information of the video;

Means for dividing the video into a plurality of segments according to the video scene information.
The apparatus according to claim 13, wherein the means for dividing the video into a plurality of segments according to the video scene information comprises:

And a device for determining, when the at least two video scenes in the video are identical or related according to the video scene information, the video segment corresponding to the at least two video scenes as one segment of the video.
The apparatus of claim 11, wherein the means for obtaining segmentation evaluation information corresponding to each of the plurality of segments comprises:

Means for determining, for each segment, the segmentation evaluation information corresponding to the segment according to the vital information of the user during viewing of the segment.
The apparatus of claim 11, wherein the means for obtaining segmentation evaluation information corresponding to each of the plurality of segments comprises:

Means for determining, for each segment, the segmentation evaluation information corresponding to the segment according to the interaction operation information during the viewing of the segment by the user.
The apparatus of claim 11, wherein the means for obtaining segmentation evaluation information corresponding to each of the plurality of segments comprises:

Means for determining, for each segment, the segmentation evaluation information of the segment according to the playback record information of the segment.
The device of claim 11 wherein the device further comprises:

Means for obtaining weight information for each of the segments;

The device for determining the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment includes:

And means for determining the evaluation result information of the video according to the segmentation evaluation information corresponding to each segment and combining the weight information of each segment.
The apparatus of claim 18, wherein the means for obtaining weight information for each of the segments comprises:

Means for determining, for each of the segments, weight information for the segment based on the presentation characteristic information of the particular visual object of the video in the segment.
The device according to any one of claims 11 to 19, wherein the device further comprises:

Means for sorting the plurality of videos based on the evaluation result information of each of the plurality of videos.
A computer readable medium having stored thereon a computer program, the computer program being executable by a processor, according to any one of claims 1 to 10.
A computer program product, when the computer program product is executed by a computer device, the method of any one of claims 1 to 10 being performed.
A computer device, the computer device comprising:

a memory for storing one or more computer programs;

One or more processors coupled to the memory,

The one or more processors are caused to perform the method of any one of claims 1 to 10 when the one or more computer programs are executed by the one or more processors.