CN108062409B - Live video abstract generation method and device and electronic equipment - Google Patents

Live video abstract generation method and device and electronic equipment Download PDF

Info

Publication number
CN108062409B
CN108062409B CN201711470643.2A CN201711470643A CN108062409B CN 108062409 B CN108062409 B CN 108062409B CN 201711470643 A CN201711470643 A CN 201711470643A CN 108062409 B CN108062409 B CN 108062409B
Authority
CN
China
Prior art keywords
live broadcast
live
segments
segment
highlight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201711470643.2A
Other languages
Chinese (zh)
Other versions
CN108062409A (en
Inventor
吴金贵
彭瑾龙
傅一峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201711470643.2A priority Critical patent/CN108062409B/en
Publication of CN108062409A publication Critical patent/CN108062409A/en
Application granted granted Critical
Publication of CN108062409B publication Critical patent/CN108062409B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/738—Presentation of query results
    • G06F16/739—Presentation of query results in form of a video summary, e.g. the video summary being a video sequence, a composite still image or having synthesized frames

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The embodiment of the invention provides a live broadcast video abstract generation method, a live broadcast video abstract generation device and electronic equipment.

Description

Live video abstract generation method and device and electronic equipment
Technical Field
The invention relates to the technical field of video abstract generation, in particular to a live video abstract generation method and device.
Background
The current live broadcast platform only has a live broadcast video recording and broadcasting function, and a user can only know the style and the characteristics of a certain anchor broadcast by watching live broadcast or recording and broadcasting playback, but because representative wonderful content in live broadcast has instantaneity, the user often needs to spend a long watching time to know the style and the characteristics of the anchor broadcast. Therefore, how to make users know the style and features of the anchor more conveniently and quickly is a great need for the anchor platform.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for generating a live video abstract, which are used for automatically generating the live video abstract of each anchor. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for generating a live video summary, including:
from live broadcast, acquiring live broadcast segments with a first duration every other time period of the first duration;
acquiring the number of users watching each live broadcast segment with the first time length and the number of messages sent by the users, inputting the acquired number of users and the number of messages into a preset wonderful degree calculation formula, and calculating the wonderful degree of each live broadcast segment with the first time length;
according to the wonderful degree of each live broadcast segment with the first time length, selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first time length to obtain wonderful live broadcast segments;
and synthesizing the wonderful live broadcast segments into a live broadcast video abstract, and displaying the live broadcast video abstract in a live broadcast room interface corresponding to the anchor broadcast.
Optionally, the step of obtaining a live broadcast segment of a first duration every other time period from the start of live broadcast includes:
acquiring a live broadcast segment with a first duration through continuous sampling; the continuous sampling is that when two adjacent live broadcast segments are obtained within the time period of the first duration, the time interval is 0;
and discarding the last section of live broadcast clip obtained when the live broadcast stops each time.
Optionally, the step of obtaining the number of users watching the live broadcast segments of each first duration and the number of messages sent by the users, inputting the obtained number of users and the obtained number of messages into a preset wonderful degree calculation formula, and calculating the wonderful degree of the live broadcast segments of each first duration includes:
acquiring the number of users watching the live broadcast segments of each first time length when the live broadcast segments of each first time length are finished;
acquiring the number of messages which are sent by a user and correspond to the live broadcast segments of each first time length within the first time length;
calculating the wonderful degree of each live broadcast segment with the first duration by using a preset wonderful degree calculation formula according to the number of the users and the number of the messages;
the preset wonderful degree calculation formula is as follows:
Figure GDA0003061849960000021
wherein t is the first duration, p is the number of users, m is the number of messages, and w is the wonderful degree of the live broadcast segment of the first duration.
Optionally, the step of selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration to obtain wonderful live broadcast segments includes:
selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration as to-be-processed live broadcast segments;
adding supplementary segments with second time length at the head and tail of each live segment to be processed to obtain a wonderful live segment with third time length;
the third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
Optionally, the step of selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration to obtain wonderful live broadcast segments may further include:
selecting the live broadcast segment with the highest wonderful degree from the live broadcast segments with the first duration as a first live broadcast segment to be processed; adding supplementary segments with second time length at the head and the tail of the first live segment to be processed to obtain a first highlight live segment with third time length;
selecting a next live broadcast segment to be processed meeting a selection rule according to the first highlight live broadcast segment; adding supplementary segments with second time length at the head and tail of the next live segment to be processed to obtain a highlight live segment with third time length;
the currently generated highlight live broadcast segment is always used as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed, and the live broadcast segments with the first duration are traversed according to the selection rule until a second preset number of live broadcast segments to be processed are selected;
the third duration is the sum of the first duration and the second duration; the supplementary segments are live segments without time intervals between the live segments and the head and the tail of each live segment to be processed in live broadcasting;
the selection rule is as follows: and excluding the first highlight live broadcast segment from the live broadcast segments with the first time length, and excluding the live broadcast segments with the fourth time length before and after the first highlight live broadcast segment and without time intervals between the first highlight live broadcast segments, wherein the remaining live broadcast segments with the highest highlight degree in the live broadcast segments with the first time length are the next live broadcast segments to be processed, which meet the selection rule.
Optionally, the step of adding supplementary segments with a second duration at the beginning and the end of the live segment to be processed as the highlight live segment further includes:
and when the supplementary segments with the second time length are respectively added at the head and the tail of the live broadcast segment to be processed, if the time length of the supplementary segments is less than the second time length, the live broadcast segment to be processed is dropped.
Optionally, the step of synthesizing the highlight live broadcast segments into live broadcast video summaries and displaying the live broadcast video summaries in a live broadcast room interface corresponding to the anchor broadcast includes:
sorting the highlight live broadcast segments in a descending order according to the highlight degrees of the corresponding live broadcast segments, and synthesizing the highlight live broadcast segments into a current live broadcast video abstract;
and displaying the current live video abstract in a live broadcasting room interface corresponding to the anchor.
Optionally, after the step of displaying the current live video summary in the live room interface of the corresponding anchor, the method further includes:
and playing the current live video abstract according to the sequence that the highlight degree of the highlight live clip corresponding to the highlight live clip is presented from high to low.
Optionally, after the step of synthesizing the highlight live broadcast clip into a live broadcast video summary and displaying the live broadcast video summary in a live broadcast interface corresponding to the anchor, the method further includes:
the method comprises the steps that from each new live broadcast, every other time period of first time duration, a live broadcast segment of first time duration corresponding to the new live broadcast, the number of users watching the live broadcast segment and the number of messages sent by the users are obtained, and the wonderness degree of the live broadcast segment in the new live broadcast is calculated by utilizing a preset wonderness degree calculation formula;
comparing the wonderful degree of the live broadcast segments in the new live broadcast with the minimum wonderful degree of the live broadcast segments corresponding to all the wonderful live broadcast segments in the live broadcast video summary displayed currently, and if the wonderful degree of the live broadcast segments in the new live broadcast is greater than the minimum wonderful degree, generating the wonderful live broadcast segments of the live broadcast segments in the new live broadcast;
and updating the highlight live broadcast segment corresponding to the minimum highlight degree in the currently displayed live broadcast video abstract into the highlight live broadcast segment of the live broadcast segment in the new live broadcast.
In a second aspect, an embodiment of the present invention provides a device for generating a live video summary, including:
the live broadcast clip acquisition module is used for acquiring a live broadcast clip with a first duration every other time period from the beginning of live broadcast;
the wonderful degree calculation module is used for acquiring the number of users watching the live broadcast segments of each first time length and the number of messages sent by the users, inputting the acquired number of users and the number of messages into a preset wonderful degree calculation formula, and calculating the wonderful degree of the live broadcast segments of each first time length;
the highlight live broadcast segment acquisition module is used for selecting a first preset number of live broadcast segments with the highest highlight degree from the live broadcast segments with the first time length according to the highlight degree of the live broadcast segments with the first time length to obtain highlight live broadcast segments;
and the live video abstract generating module is used for synthesizing the wonderful live broadcast fragments into a live video abstract and displaying the live video abstract in a live broadcast room interface corresponding to the anchor broadcast.
Optionally, the live broadcast segment obtaining module is specifically configured to:
acquiring a live broadcast segment with a first duration through continuous sampling; the continuous sampling is that when two adjacent live broadcast segments are obtained within the time period of the first duration, the time interval is 0;
and discarding the last section of live broadcast clip obtained when the live broadcast stops each time.
Optionally, the wonderful degree calculating module is specifically configured to:
acquiring the number of users watching the live broadcast segments of each first time length when the live broadcast segments of each first time length are finished;
acquiring the number of messages which are sent by a user and correspond to the live broadcast segments of each first time length within the first time length;
calculating the wonderful degree of each live broadcast segment with the first duration by using a preset wonderful degree calculation formula according to the number of the users and the number of the messages;
the preset wonderful degree calculation formula is as follows:
Figure GDA0003061849960000051
wherein t is the first duration, p is the number of users, m is the number of messages, and w is the wonderful degree of the live broadcast segment of the first duration.
Optionally, the highlight live broadcast segment obtaining module is specifically configured to:
selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration as to-be-processed live broadcast segments;
adding supplementary segments with second time length at the head and tail of each live segment to be processed to obtain a wonderful live segment with third time length;
the third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
Optionally, the highlight live broadcast segment obtaining module includes:
the first obtaining submodule is used for selecting the live broadcast segment with the highest wonderful degree from the live broadcast segments with the first duration as a first to-be-processed live broadcast segment; adding supplementary segments with second time length at the head and the tail of the first live segment to be processed to obtain a first highlight live segment with third time length;
the second acquisition submodule is used for selecting the next live broadcast segment to be processed which meets the selection rule according to the first highlight live broadcast segment; adding supplementary segments with second time length at the head and tail of the next live segment to be processed to obtain a highlight live segment with third time length;
the currently generated highlight live broadcast segment is always used as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed, and the live broadcast segments with the first duration are traversed according to the selection rule until a second preset number of live broadcast segments to be processed are selected;
the third duration is the sum of the first duration and the second duration; the supplementary segments are live segments without time intervals between the live segments and the head and the tail of each live segment to be processed in live broadcasting;
the selection rule is as follows: and excluding the first highlight live broadcast segment from the live broadcast segments with the first time length, and excluding the live broadcast segments with the fourth time length before and after the first highlight live broadcast segment and without time intervals between the first highlight live broadcast segments, wherein the remaining live broadcast segments with the highest highlight degree in the live broadcast segments with the first time length are the next live broadcast segments to be processed, which meet the selection rule.
Optionally, the highlight live broadcast segment obtaining module is specifically configured to:
and when the supplementary segments with the second time length are respectively added at the head and the tail of the live broadcast segment to be processed, if the time length of the supplementary segments is less than the second time length, the live broadcast segment to be processed is dropped.
Optionally, the live video summary generation module is specifically configured to:
sorting the highlight live broadcast segments in a descending order according to the highlight degrees of the corresponding live broadcast segments, and synthesizing the highlight live broadcast segments into a current live broadcast video abstract;
and displaying the current live video abstract in a live broadcasting room interface corresponding to the anchor.
Optionally, the live video summary generation module is specifically configured to:
and playing the current live video abstract according to the sequence that the highlight degree of the highlight live clip corresponding to the highlight live clip is presented from high to low.
Optionally, the apparatus further includes a highlight live-broadcast segment updating module, specifically configured to:
the method comprises the steps that from each new live broadcast, every other time period of first time duration, a live broadcast segment of first time duration corresponding to the new live broadcast, the number of users watching the live broadcast segment and the number of messages sent by the users are obtained, and the wonderness degree of the live broadcast segment in the new live broadcast is calculated by utilizing a preset wonderness degree calculation formula;
comparing the wonderful degree of the live broadcast segments in the new live broadcast with the minimum wonderful degree of the live broadcast segments corresponding to all the wonderful live broadcast segments in the live broadcast video summary displayed currently, and if the wonderful degree of the live broadcast segments in the new live broadcast is greater than the minimum wonderful degree, generating the wonderful live broadcast segments of the live broadcast segments in the new live broadcast;
and updating the highlight live broadcast segment corresponding to the minimum highlight degree in the currently displayed live broadcast video abstract into the highlight live broadcast segment of the live broadcast segment in the new live broadcast.
In a third aspect, an embodiment of the present invention provides an electronic device, which is characterized by including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;
a memory for storing a computer program;
a processor configured to implement the method steps of the first aspect when executing the program stored in the memory.
According to the live broadcast video abstract generation method, the live broadcast video abstract generation device and the electronic equipment, the wonderful degree of each live broadcast segment is calculated through the live broadcast segments obtained from the live broadcast, the number of the users corresponding to the live broadcast segments and the number of the messages sent by the users, so that the wonderful live broadcast segments are obtained according to the wonderful degree of the live broadcast segments, the wonderful live broadcast segments are synthesized into the abstract, a live broadcast video abstract can be automatically generated for each anchor, and the style and the characteristics of the anchor can be more conveniently and quickly known to the users. Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.
Fig. 1 is a flowchart of a method for generating a live video summary according to an embodiment of the present invention;
fig. 2 is another flowchart of a method for generating a live video summary according to an embodiment of the present invention;
fig. 3 is a structural diagram of a device for generating a live video summary according to an embodiment of the present invention;
fig. 4 is another structural diagram of a live video summary generation apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention;
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention.
First, a method for generating a live video summary according to an embodiment of the present invention is described below.
It should be noted that the method for generating a live video summary provided in the embodiment of the present invention may be applied to an electronic device capable of providing a live service, where the device includes a desktop computer, a portable computer, an internet television, an intelligent mobile terminal, a wearable intelligent terminal, a server, and the like, and is not limited herein, and any electronic device that can implement the embodiment of the present invention belongs to the protection scope of the embodiment of the present invention.
As shown in fig. 1, a process of a method for generating a live video summary according to an embodiment of the present invention may include:
s101, from live broadcast, acquiring live broadcast segments with a first duration every other time period of the first duration.
The live broadcast is started from the anchor broadcast, the live broadcast is sampled every a time period of a first time length, and one collected sampling segment is a live broadcast segment of the first time length, wherein the first time length can be a preset time length. Therefore, the segmentation of the anchor live broadcast is realized, and the live broadcast content which can embody the style and the characteristics of the anchor can be extracted conveniently in the follow-up process.
S102, acquiring the number of users watching the live broadcast segments of each first time length and the number of messages sent by the users, inputting the acquired number of users and the number of messages into a preset wonderful degree calculation formula, and calculating the wonderful degree of the live broadcast segments of each first time length.
Generally, the live broadcast content which can best embody the style and the characteristics of the anchor is live broadcast wonderful content, and when the wonderful content appears in the live broadcast, the number of messages sent by audiences watching the wonderful content is increased. Therefore, for each live broadcast segment with the first duration, the number of users watching the live broadcast segment and the number of messages sent by the users can be acquired, the acquired number of users and the acquired number of messages are input into a preset wonderful degree calculation formula, and the wonderful degree of each live broadcast segment with the first duration is calculated. The wonderful degree enables different wonderful contents of different live broadcast segments to be compared according to a unified standard, and therefore the live broadcast content which can most embody the style and the characteristics of the anchor can be conveniently extracted from the live broadcast segments with the first duration in the follow-up process. The wonderful degree calculation formula is a mathematical operation relation between the wonderful degree and the number of the users and the number of the messages.
S103, selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first time length according to the wonderful degree of the live broadcast segments with the first time length to obtain wonderful live broadcast segments.
And S104, synthesizing the wonderful live broadcast segments into live broadcast video summaries, and displaying the live broadcast video summaries in a live broadcast room interface corresponding to the anchor broadcast.
The more highlights the content of the live segment, the higher the highlight of the segment. Therefore, a first preset number of live broadcast segments with the highest wonderful degree are selected from the live broadcast segments with the first duration, and the live broadcast segments can be used as wonderful live broadcast segments to be synthesized into a live broadcast video abstract. For example: and selecting 5 live broadcast segments with the highest wonderful degree from the obtained 60 live broadcast segments of 1 minute, wherein the wonderful degrees of the 5 live broadcast segments are sequentially 10, 9, 8, 7 and 6 which are higher than those of the rest 55 live broadcast segments, synthesizing the 5 live broadcast segments into live broadcast video summaries, and displaying the live broadcast video summaries in a live broadcast interface corresponding to the anchor broadcast.
According to the method, when a plurality of wonderful live broadcast contents are extracted, the wonderful live broadcast segments are automatically synthesized into the live broadcast video abstract and displayed in the live broadcast room interface corresponding to the anchor broadcast. When a user wants to know a certain main broadcast, the user can watch essence parts of the main broadcast in multiple times of live broadcast in a short time as long as watching the live broadcast video abstract in the interface of the main broadcast live broadcast room, so that the problem that the user needs to spend a large amount of time to watch the whole live broadcast or historical playback of the main broadcast in multiple times in the traditional method is solved, and the user can know the style and the characteristics of the main broadcast more conveniently and quickly.
Optionally, step S101 in the embodiment shown in fig. 1 may specifically include:
acquiring a live broadcast segment with a first duration through continuous sampling; the continuous sampling is that when two adjacent live broadcast segments are obtained within the time period of the first duration, the time interval is 0.
For example: setting the first time length as 1 minute, and when the live broadcast start time is 14:00, the process of obtaining the live broadcast segment with the first time length through continuous sampling comprises the following steps: 14:01 live segments A of 14:00-14:01, 14:02 live segments B of 14:01-14:02, and the time interval between two adjacent live segments A, B is 0 within 1 minute of 14:01-14: 02. The live broadcast clip with the first duration can be ensured to be the live broadcast clip containing all the wonderful contents by a continuous sampling mode, and any wonderful contents are prevented from being omitted.
And discarding the last section of live broadcast clip obtained when the live broadcast stops each time.
Generally, the time length of the last segment of the sampled section acquired when the live broadcasting stops is smaller than that of the previous sampled section, and the main broadcasting has no wonderful performance in the time period before the live broadcasting stops, so that the last segment of the live broadcasting section acquired when each live broadcasting stops can be dropped. Therefore, inconspicuous redundant live broadcast segments are reduced, the live broadcast video summary generation efficiency is improved, and the equal length of the live broadcast segments is ensured for the sampling method with the same time length in the embodiment.
Optionally, step S102 in the embodiment shown in fig. 1 may specifically include:
and acquiring the number of users watching the live broadcast clips with the first duration when the live broadcast clips with the first duration are finished.
In each live broadcast process, partial users enter or leave the live broadcast room at variable time, and meanwhile if the live broadcast content is wonderful enough, the users are attracted to stay in the live broadcast room to continue watching, so that for each live broadcast segment with the first time length, the number of the users in the live broadcast room at the end of the live broadcast segment is uniformly used as the number of the users watching the live broadcast segment.
For example: when the first time length is 1 minute, the live broadcast of a certain anchor starts from 14:00, and the obtained live broadcast segment A is live broadcast content of 14:00 to 14:01, the number of users in the live broadcast room of the anchor is obtained when the live broadcast segment A is finished, namely 14:01, and it can be understood that the users in the live broadcast room are users watching the live broadcast. Compared with the method for directly obtaining the number of users watching the live broadcast segments of each first time length in the time period of the first time length, the method eliminates the number of invalid users, and is beneficial to obtaining more accurate wonderful degree of the live broadcast segments of each first time length subsequently.
And acquiring the number of messages which are sent by the user within the first time length and correspond to the live broadcast segments of each first time length.
It can be understood that the fact that the user sends the message in the live broadcast represents "cheering" the live broadcast content, that is, the user who sends the message generally does not leave the live broadcast, so that when the number of messages sent by the user is obtained, the number of messages sent by the user in the first time period corresponding to the live broadcast segment can be directly obtained. For example: when the first time length is 1 minute, the live broadcast of a certain anchor starts from 14:00, and the obtained live broadcast segment A is live broadcast content of 14:00-14:01, the number of messages sent by the user in a time period of 14:00-14:01 is obtained.
After the number of users and the number of messages are obtained in the above optional manner, the preset wonderful degree calculation formula may be:
Figure GDA0003061849960000101
wherein t is the first duration, p is the number of users, m is the number of messages, and w is the wonderful degree of the live broadcast segment of the first duration.
It can be understood that the setting of t needs to guarantee the accuracy of the obtained wonderful degree, and too big t can lead to the live broadcast segment overlength of acquireing and contain more redundant information, makes the wonderful degree of this segment of acquireing inaccurate enough, and too little t can increase the calculated amount and reduce efficiency, and because live video segmentation undersize can lead to the calculating of wonderful degree happily higher. Therefore, t can be set according to historical experience, or according to the current transmission rate of the live video when the live segment is acquired. For example: the value of t may be set to 10 seconds, or, alternatively, greater than 10 seconds.
T is set according to historical experience. Whether the obtained wonderful degree corresponds to the actual wonderful condition of each live broadcast segment content or not can be determined by analyzing and comparing in advance when a large number of live broadcast videos are sampled at different t, so that a proper value is determined. For example: when t is 10 seconds, the obtained highlight degree value of each live broadcast segment corresponds to the actual highlight condition of each live broadcast segment, and then t can be set to be 10 seconds.
Or setting t according to the transmission rate of the live video when the live clip is acquired. Because live broadcasting is a real-time video stream transmission technology, the transmission rate changes due to the influence of the transmission environment in the transmission process, the transmission rate is high when the transmission environment is good, the live video streams transmitted in a certain time are more, the transmission rate is low when the transmission environment is poorer, and the live video streams transmitted in a certain time are less. For example: when the transmission rate is fast, the live broadcast content transmitted within 10 seconds is a sentence for the main broadcast, and the transmissionAt slow rates, live content transmitted within 10 seconds has not been spoken for the anchor. Therefore, t can be adaptively set according to the current transmission rate of the live video on the basis of t set according to historical experience. The method specifically comprises the following steps: before each live broadcast segment is acquired, the current transmission rate of the live broadcast video is acquired, and the current transmission rate is compared with a preset rate threshold value. If the current transmission rate is greater than or equal to a preset rate threshold, acquiring a live broadcast segment with a first duration every other time period of the first duration; if the current transmission rate is smaller than a preset rate threshold, acquiring a live broadcast segment with a fifth time length every a time period of the fifth time length; wherein the fifth duration is greater than the first duration. For example: before a live broadcast segment with the duration of t is obtained, the current transmission rate v of a live broadcast video is obtained, and v is compared with a preset rate threshold value v0In which a predetermined rate threshold v is set0The average transmission rate of the live video is set according to historical experience. If v ≧ v0Then t is set to the historical empirical value of 10 seconds, if v<v0Then t may be set to 12 seconds. It will be appreciated that at v<v0Under the condition, the delay of the obtained live broadcast segment content caused by the slow transmission rate of the live broadcast video can be avoided by properly increasing the sampling first time length t, so that the wonderful degree of the obtained live broadcast segment with the first time length can be more accurate. The specific setting of the first duration t may also be any other manner, and any setting manner of t that can make the obtained highlight degree of the live broadcast segment of the first duration sufficiently accurate may be used in the present invention, which is not limited in this embodiment.
The wonderful degree obtaining method is characterized in that the wonderful degree of the live broadcast segment with the first time length is represented by the number of messages sent by a unit user in unit time, so that the quantized wonderful degree of the live broadcast segment with the time length of t can be obtained by the method no matter t is set according to historical experience or t is adaptively set according to the current transmission rate of a live broadcast video when the live broadcast segment is obtained, namely any live broadcast video segmentation mode.
Optionally, step S103 in the embodiment shown in fig. 1 may specifically include:
selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration as to-be-processed live broadcast segments; adding supplementary segments with second time length at the head and tail of each live segment to be processed to obtain a wonderful live segment with third time length; the third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
For example: and selecting 5 live broadcast segments with the highest wonderful degree from the live broadcast segments with the first time length as live broadcast segments to be processed, and adding 25 seconds of supplementary segments at the head and tail of the 5 live broadcast segments to be processed to obtain 5 wonderful live broadcast segments with the time length of 1 minute. The supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting. For example, if a certain live segment of the 5 live segments to be processed is a segment between 60 seconds and 70 seconds of the live video, the supplementary segments of the live segment are segments between 35 seconds and 60 seconds and segments between 70 seconds and 95 seconds of the live video. Since the user often starts sending messages after watching the main-broadcast wonderful performance in the live broadcast, the increase of the number of messages has a certain time delay. Meanwhile, due to the real-time property of live video, the transmission of live content is influenced by the transmission environment, and the transmission of live content has certain time delay. Therefore, compared with the method of directly selecting the highlight live broadcast segment from the obtained live broadcast segments according to the highlight degree, the method of the embodiment supplements the supplement segment with the third time length at the head of the live broadcast segment to be processed, thereby ensuring the correspondence between the message quantity and the highlight live broadcast segment, namely ensuring that the obtained highlight live broadcast segment is sufficiently highlighted, covering the beginning and the end of the highlight segment, and ensuring that the content of the highlight live broadcast segment watched by the user is as complete and coherent as possible.
According to the method for generating the live broadcast video abstract, the wonderful degree of each live broadcast segment is calculated through the live broadcast segments obtained from the live broadcast, the number of the users corresponding to the live broadcast segments and the number of the messages sent by the users, so that the wonderful live broadcast segments are obtained by performing supplementary processing on the live broadcast segments according to the wonderful degree of the live broadcast segments, the wonderful live broadcast segments are synthesized into the abstract, a live broadcast video abstract containing complete and continuous wonderful live broadcast segments as far as possible can be automatically generated for each anchor, and the style and the characteristics of the anchor can be more conveniently and quickly known by the users.
As shown in fig. 2, another flow of the method for generating a live video summary according to the embodiment of the present invention may include:
steps S201 and S202 correspond to steps S101 and S102 of the embodiment shown in fig. 1, respectively, and will not be described here, and refer to the foregoing description of the embodiment of fig. 1.
S203, selecting the live broadcast segment with the highest wonderful degree from the live broadcast segments with the first duration as a first live broadcast segment to be processed; and adding supplementary segments with second time length at the head and the tail of the first to-be-processed live segment to obtain a first highlight live segment with third time length.
The third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
S204, selecting the next live broadcast segment to be processed meeting the selection rule according to the first highlight live broadcast segment; and adding supplementary segments with second time length at the head and tail of the next live segment to be processed to obtain a highlight live segment with third time length.
The selection rule is as follows: and excluding the first highlight live broadcast segment from the live broadcast segments with the first time length, and excluding the live broadcast segments with the fourth time length before and after the first highlight live broadcast segment and without time intervals between the first highlight live broadcast segments, wherein the remaining live broadcast segments with the highest highlight degree in the live broadcast segments with the first time length are the next live broadcast segments to be processed, which meet the selection rule. The fourth time period may be a time period preset according to historical experience.
S205, the currently generated highlight live broadcast segment is always used as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed, and the live broadcast segments with the first time length are traversed according to the selection rule until a second preset number of live broadcast segments to be processed are selected.
For example: the first time length is 10 seconds, the second time length is 25 seconds, the third time length is 1 minute, the fourth time length is 29 minutes and 30 seconds, a live broadcast segment A to be processed with the highest wonderful degree is selected from 18000 live broadcast segments with the time lengths of 10 seconds as a first live broadcast segment to be processed, the live broadcast segment A is a segment from 180 minutes to 180 minutes and 10 seconds in a live broadcast video, the segment from 179 minutes to 35 seconds and the segment from 180 minutes to 10 seconds are respectively added to the head and the tail of the live broadcast segment A, and the obtained live broadcast segment A from 179 minutes to 35 seconds is added to 180 minutes and 35 secondsjNamely, the first highlight live broadcast segment is obtained.
After the first highlight live broadcast segment is obtained, live broadcast segments A between 179 th minute 35 seconds and 180 th minute 35 seconds are excluded from the live broadcast segments of the first durationjAnd selecting live broadcast segment B with highest wonderful degree from the rest 17640 live broadcast segments with the time length of 10 seconds as the next live broadcast segment to be processed, wherein the live broadcast segment from 150 minutes 05 seconds to 179 minutes 35 seconds and the live broadcast segment from 180 minutes 35 seconds to 210 minutes 05 seconds. Adding supplementary segments to the live broadcast segment B which is the same as the live broadcast segment B to be processed to obtain a wonderful live broadcast segment B of the live broadcast segment Bj。
At this time, the currently generated highlight live broadcast segment BjAs the first highlight live broadcast segment for selecting the next live broadcast segment to be processed, similar to the selection of the live broadcast segment B, the highlight live broadcast segment B is excluded from 17640 live broadcast segments with the time length of 10 secondsjAnd Bj29 parts before and after 30 seconds long and with BjAfter the live broadcast segments without time intervals, selecting the live broadcast segment C with the highest wonderful degree from the rest 17280 live broadcast segments with the time length of 10 seconds as the next live broadcast segment to be processed.
And taking the currently generated highlight live broadcast segment as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed all the time, and traversing each live broadcast segment with the first duration according to the selection rule until 4 live broadcast segments to be processed are selected. It can be understood that, when a live video summary containing 5 highlight live broadcast segments needs to be synthesized, the second preset number is 4, that is, except that the first to-be-processed live broadcast segment does not need to be selected according to the selection rule, the next to-be-processed live broadcast segment always needs to be selected by traversing each live broadcast segment with the first duration according to the selection rule.
Compared with the method for directly selecting the live broadcast segments with the highest wonderful degree from the live broadcast segments with the first time length to serve as the live broadcast segments to be processed and processing the live broadcast segments to be processed to obtain the wonderful live broadcast segments, the embodiment shown in the figure 2 ensures that the obtained wonderful live broadcast segments are wonderful enough through the technical means of segment supplement, ensures that the contents of the wonderful segments watched by a user are as complete and coherent as possible, and ensures that the selected wonderful live broadcast segments can contain various contents while the selected wonderful live broadcast segments are not overlapped with each other through the technical means of the selection rule so as to display the wonderful live broadcast segments with different characteristics or styles of main broadcast.
In practical application, before step S203, it may be determined whether the total duration of the anchor live broadcast can ensure that the to-be-processed live broadcast segment can be selected always according to the selection rule. If so, a live video summary is generated for the anchor. For example: and when the third time length is 1 minute, the fourth time length in the selection rule is 29 minutes and 30 seconds, and the generated summary contains 5 wonderful live broadcast segments, firstly judging whether the live broadcast total time length of the anchor is more than or equal to 5 hours. If the total live broadcast duration of the anchor is more than or equal to 5 hours, executing S204 and the subsequent steps; if the total live broadcast time length of the anchor is less than 5 hours, the data obtained in the steps S201 to S202 are saved, the steps S201 to S202 are continuously executed for the new live broadcast of the anchor until the total live broadcast time length of the anchor reaches 5 hours, and then the step S204 and the subsequent steps are executed. Of course, the specific setting of each duration in the present invention is not limited in this embodiment, and any setting that can be used to achieve the above technical effects can be used in the present invention.
Optionally, as for the supplementary segments that are added with the second duration at the beginning and the end of the live segment to be processed in the foregoing embodiment, as the step of the highlight live segment, the method may further include:
and when the supplementary segments with the second time length are respectively added at the head and the tail of the live broadcast segment to be processed, if the time length of the supplementary segments is less than the second time length, the live broadcast segment to be processed is dropped. For example, the segment to be processed is a segment between 10 seconds and 20 seconds of the live video, the live video before the start of the segment is only 10 seconds and less than 25 seconds, that is, the segment to be supplemented has only 10 seconds, so that the segment to be supplemented with the segment having the duration of 25 seconds cannot be supplemented, and the segment to be processed is discarded.
Step S206, corresponding to step S104 of the embodiment shown in fig. 1, is not described here, and the foregoing description of the embodiment of fig. 1 is referred to in detail.
Optionally, the step S104 or the step S206 of synthesizing the highlight live broadcast segment into a live broadcast video summary and displaying the live broadcast video summary in a live broadcast interface corresponding to the anchor may specifically include:
sorting the highlight live broadcast segments in a descending order according to the highlight degrees of the corresponding live broadcast segments, and synthesizing the highlight live broadcast segments into a current live broadcast video abstract; and displaying the current live video abstract in a live broadcasting room interface corresponding to the anchor.
And playing the current live video abstract according to the sequence that the highlight degree of the highlight live clip corresponding to the highlight live clip is presented from high to low.
For example, 5 highlights of a certain anchor are in descending order of the highlights of the corresponding live segments as Aj、Bj、Cj、Dj、EjThe synthesized current live video abstract is a video of 5 minutes and is displayed in the interface between the anchor players, and when the current live video abstract is played, a user firstly sees the most wonderful degreeHigh wonderful live broadcast segment AjThen in turn is Bj、Cj、Dj、Ej. It can be understood that the method enables the user to firstly view the most wonderful live broadcast segment of the anchor, namely the live broadcast content which can embody the features and styles of the anchor, and further improves the efficiency of the user in knowing the features and styles of the anchor.
Optionally, after step S104 or step S206 of synthesizing the highlight live broadcast segment into a live broadcast video summary and displaying the live broadcast video summary in a live broadcast interface corresponding to the anchor, the method may further include the following steps:
and from each new live broadcast, acquiring a live broadcast segment with a first time length corresponding to the new live broadcast, the number of users watching the live broadcast segment and the number of messages sent by the users every other time period of the first time length, and calculating the wonderful degree of the live broadcast segment in the new live broadcast by using a preset wonderful degree calculation formula.
And comparing the wonderful degree of the live broadcast segments in the new live broadcast with the minimum wonderful degree of the live broadcast segments corresponding to all the wonderful live broadcast segments in the live broadcast video abstract displayed currently, and if the wonderful degree of the live broadcast segments in the new live broadcast is greater than the minimum wonderful degree, generating the wonderful live broadcast segments of the live broadcast segments in the new live broadcast.
And updating the highlight live broadcast segment corresponding to the minimum highlight degree in the currently displayed live broadcast video abstract into the highlight live broadcast segment of the live broadcast segment in the new live broadcast.
The method comprises the steps of firstly calculating the wonderful degree of a live broadcast segment for each new live broadcast of a main broadcast every time when the live broadcast segment with the first duration is obtained, then comparing the wonderful degree of the new live broadcast segment with the minimum wonderful degree of the live broadcast segment corresponding to each wonderful live broadcast segment displayed in a live broadcast video abstract of the main broadcast interface currently, if the wonderful degree of the new live broadcast segment is larger than the minimum wonderful degree, regenerating the wonderful live broadcast segment of the new live broadcast segment, and replacing the wonderful live broadcast segment corresponding to the minimum wonderful degree in a live broadcast video abstract displayed currently with the new wonderful live broadcast segment. Compared with the method of directly executing the steps S101 to S102, or the steps S101 to S103, or the steps S201 to S202, or the steps S201 to S204, and then comparing the degrees of highlights to determine whether to update, the updating method of comparing the degrees of highlights adopted in the embodiment avoids generating the live highlight clip for the live highlight clip corresponding to the live highlight clip with the degree of highlights being smaller than the minimum degree of highlights in the currently displayed live video summary, which not only improves the updating efficiency, but also avoids resource waste.
According to the method for generating the live broadcast video abstract, the wonderful degree of each live broadcast segment is calculated through the live broadcast segments obtained from the live broadcast, the number of the users corresponding to the live broadcast segments and the number of the messages sent by the users, so that the live broadcast segments are subjected to supplementary processing according to the wonderful degree of the live broadcast segments and the selection rule to obtain the wonderful live broadcast segments, the wonderful live broadcast segments are synthesized into the abstract, each anchor broadcast can be automatically generated with a live broadcast video abstract containing the wonderful live broadcast segments which are as complete and continuous as possible and have unrepeated contents, and the user can know the style and the characteristics of the anchor broadcast more conveniently and quickly.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a device for generating a live video summary.
As shown in fig. 3, a structure of an apparatus for generating a live video summary according to an embodiment of the present invention may include:
the live broadcast segment acquiring module 301 is configured to acquire a live broadcast segment with a first duration every a time period of the first duration from the start of live broadcast.
The highlight calculation module 302 is configured to obtain the number of users watching the live broadcast segments of each first duration and the number of messages sent by the users, and calculate the highlight of the live broadcast segments of each first duration by using a preset highlight calculation formula.
The highlight live broadcast segment obtaining module 303 is configured to select, from the live broadcast segments with the first duration, a first preset number of live broadcast segments with the highest highlight degree according to the highlight degree of the live broadcast segment with the first duration, so as to obtain a highlight live broadcast segment.
And the live video summary generation module 304 is configured to synthesize the highlight live clips into a live video summary, and display the live video summary in a live room interface corresponding to the anchor.
Optionally, the live broadcast segment obtaining module is specifically configured to:
acquiring a live broadcast segment with a first duration through continuous sampling; the continuous sampling is that when two adjacent live broadcast segments are obtained within the time period of the first duration, the time interval is 0;
and discarding the last section of live broadcast clip obtained when the live broadcast stops each time.
Optionally, the wonderful degree calculating module is specifically configured to:
and acquiring the number of users watching the live broadcast clips with the first duration when the live broadcast clips with the first duration are finished.
And acquiring the number of messages which are sent by the user within the first time length and correspond to the live broadcast segments of each first time length.
Calculating the wonderful degree of each live broadcast segment with the first duration by using a preset wonderful degree calculation formula according to the number of the users and the number of the messages;
the preset wonderful degree calculation formula is as follows:
Figure GDA0003061849960000171
wherein t is the first duration, p is the number of users, m is the number of messages, and w is the wonderful degree of the live broadcast segment of the first duration.
Optionally, the highlight live broadcast segment obtaining module is specifically configured to:
and selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration as to-be-processed live broadcast segments.
And adding supplementary segments with second time length at the head and tail of each live segment to be processed to obtain a wonderful live segment with third time length.
The third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
The device for generating the live broadcast video summary provided by the embodiment of the invention calculates the wonderful degree of each live broadcast segment through the live broadcast segments obtained from the live broadcast, the number of the users corresponding to the live broadcast segments and the number of the messages sent by the users, so that the wonderful live broadcast segments are obtained and a wonderful live broadcast segment collection is generated according to the wonderful degree of the live broadcast segments, a live broadcast wonderful collection can be automatically generated for each anchor, and the user can know the style and the characteristics of the anchor more conveniently and quickly.
As shown in fig. 4, another structure of a device for generating a live video summary according to an embodiment of the present invention may include:
the modules 401 and 402 correspond to the modules 301 and 302 of the embodiment shown in fig. 3, and will not be described here, and refer to the foregoing description of the embodiment of fig. 3.
The highlight live clip obtaining module 403 may include:
the first obtaining sub-module 4031 is configured to select, from the live broadcast segments of the first duration, a live broadcast segment with the highest wonderful degree as a first to-be-processed live broadcast segment; and adding supplementary segments with second time length at the head and the tail of the first to-be-processed live segment to obtain a first highlight live segment with third time length.
A second obtaining sub-module 4032, configured to select, according to the first highlight live broadcast segment, a next to-be-processed live broadcast segment that meets a selection rule; and adding supplementary segments with second time length at the head and tail of the next live segment to be processed to obtain a highlight live segment with third time length.
And the currently generated highlight live broadcast segment is always used as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed, and the live broadcast segments with the first time length are traversed according to the selection rule until a second preset number of live broadcast segments to be processed are selected.
The third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
The selection rule is as follows: and excluding the first highlight live broadcast segment from the live broadcast segments with the first time length, and excluding the live broadcast segments with the fourth time length before and after the first highlight live broadcast segment and without time intervals between the first highlight live broadcast segments, wherein the remaining live broadcast segments with the highest highlight degree in the live broadcast segments with the first time length are the next live broadcast segments to be processed, which meet the selection rule.
The module 404, corresponding to the module 304 of the embodiment shown in fig. 3, will not be described here, and refer to the foregoing description of the embodiment of fig. 3.
Optionally, the highlight live broadcast segment obtaining module is specifically configured to:
and when the supplementary segments with the second time length are respectively added at the head and the tail of the live broadcast segment to be processed, if the time length of the supplementary segments is less than the second time length, the live broadcast segment to be processed is dropped.
Optionally, the live video summary generation module is specifically configured to:
and sequencing the highlight live broadcast segments in a descending order according to the highlight degrees of the corresponding live broadcast segments, and synthesizing the highlight live broadcast segments into the current live broadcast video abstract.
And displaying the current live video abstract in a live broadcasting room interface corresponding to the anchor.
And playing the current live video abstract according to the sequence that the highlight degree of the highlight live clip corresponding to the highlight live clip is presented from high to low.
Optionally, in another embodiment, the apparatus may further include a highlight live clip updating module, specifically configured to:
the method comprises the steps that from each new live broadcast, every other time period of first time duration, a live broadcast segment of first time duration corresponding to the new live broadcast, the number of users watching the live broadcast segment and the number of messages sent by the users are obtained, and the wonderness degree of the live broadcast segment in the new live broadcast is calculated by utilizing a preset wonderness degree calculation formula;
comparing the wonderful degree of the live broadcast segments in the new live broadcast with the minimum wonderful degree of the live broadcast segments corresponding to all the wonderful live broadcast segments in the live broadcast video summary displayed currently, and if the wonderful degree of the live broadcast segments in the new live broadcast is greater than the minimum wonderful degree, generating the wonderful live broadcast segments of the live broadcast segments in the new live broadcast;
and updating the highlight live broadcast segment corresponding to the minimum highlight degree in the currently displayed live broadcast video abstract into the highlight live broadcast segment of the live broadcast segment in the new live broadcast.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations of the invention.
The device for generating the live broadcast video summary provided by the embodiment of the invention calculates the wonderful degree of each live broadcast segment through the live broadcast segments acquired from the live broadcast, the number of users corresponding to the live broadcast segments and the number of messages sent by the users, so that the wonderful live broadcast segments are acquired according to the wonderful degree of the live broadcast segments, a live broadcast video summary can be automatically generated for each anchor broadcast, meanwhile, the live broadcast video summary generated currently is continuously updated by the live broadcast segment with the wonderful degree higher than that in the current live broadcast video summary, the live broadcast video summary is always the live broadcast video summary which can embody the wonderful expression of the anchor broadcast, and the user can know the style and the characteristics of the anchor broadcast more conveniently and quickly.
The embodiment of the present invention further provides an electronic device, as shown in fig. 5, including a processor 501, a communication interface 502, a memory 503 and a communication bus 504, where the processor 501, the communication interface 502, and the memory complete mutual communication through the communication bus 504 via the memory 503;
the memory 503 is used for storing computer programs;
the processor 501 is configured to, when executing the computer program stored in the memory 503, implement the following steps:
from live broadcast, acquiring live broadcast segments with a first duration every other time period of the first duration;
acquiring the number of users watching each live broadcast segment with the first time length and the number of messages sent by the users, and calculating the wonderful degree of each live broadcast segment with the first time length by using a preset wonderful degree calculation formula;
according to the wonderful degree of each live broadcast segment with the first time length, selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first time length to obtain wonderful live broadcast segments;
and synthesizing the wonderful live broadcast segments into a live broadcast video abstract, and displaying the live broadcast video abstract in a live broadcast room interface corresponding to the anchor broadcast.
According to the electronic equipment provided by the embodiment of the invention, the wonderful degree of each live broadcast segment is calculated through the live broadcast segments obtained from the live broadcast, the number of the users corresponding to the live broadcast segments and the number of the messages sent by the users, so that the wonderful live broadcast segments are obtained and the summaries of the wonderful live broadcast segments are generated according to the wonderful degree of the live broadcast segments, a live broadcast video summary can be automatically generated for each anchor, and the style and the characteristics of the anchor can be more conveniently and quickly known by the users.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and electronic apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims (17)

1. A method for generating a live video summary is characterized by comprising the following steps:
from live broadcast, acquiring live broadcast segments with a first duration every other time period of the first duration;
acquiring the number of users watching each live broadcast segment with the first time length and the number of messages sent by the users, inputting the acquired number of users and the number of messages into a preset wonderful degree calculation formula, and calculating the wonderful degree of each live broadcast segment with the first time length;
according to the wonderful degree of each live broadcast segment with the first time length, selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first time length to obtain wonderful live broadcast segments;
synthesizing the wonderful live broadcast segments into a live broadcast video abstract, and displaying the live broadcast video abstract in a live broadcast room interface corresponding to the anchor;
after the step of synthesizing the highlight live broadcast segments into live broadcast video summaries and displaying the live broadcast video summaries in the live broadcast room interface corresponding to the anchor broadcast, the method further comprises the following steps of:
the method comprises the steps that from each new live broadcast, every other time period of first time duration, a live broadcast segment of first time duration corresponding to the new live broadcast, the number of users watching the live broadcast segment and the number of messages sent by the users are obtained, and the wonderness degree of the live broadcast segment in the new live broadcast is calculated by utilizing a preset wonderness degree calculation formula;
comparing the wonderful degree of the live broadcast segments in the new live broadcast with the minimum wonderful degree of the live broadcast segments corresponding to all the wonderful live broadcast segments in the live broadcast video summary displayed currently, and if the wonderful degree of the live broadcast segments in the new live broadcast is greater than the minimum wonderful degree, generating the wonderful live broadcast segments of the live broadcast segments in the new live broadcast;
and updating the highlight live broadcast segment corresponding to the minimum highlight degree in the currently displayed live broadcast video abstract into the highlight live broadcast segment of the live broadcast segment in the new live broadcast.
2. The method of claim 1, wherein the step of obtaining a first-duration live segment every first-duration time period from live broadcasting comprises:
acquiring a live broadcast segment with a first duration through continuous sampling; the continuous sampling is that when two adjacent live broadcast segments are obtained within the time period of the first duration, the time interval is 0;
and discarding the last section of live broadcast clip obtained when the live broadcast stops each time.
3. The method according to claim 1, wherein the step of obtaining the number of users watching the live segments of each first duration and the number of messages sent by the users, inputting the obtained number of users and the obtained number of messages into a preset highlight calculation formula, and calculating the highlight of the live segments of each first duration comprises:
acquiring the number of users watching the live broadcast segments of each first time length when the live broadcast segments of each first time length are finished;
acquiring the number of messages which are sent by a user and correspond to the live broadcast segments of each first time length within the first time length;
calculating the wonderful degree of each live broadcast segment with the first duration by using a preset wonderful degree calculation formula according to the number of the users and the number of the messages;
the preset wonderful degree calculation formula is as follows:
Figure FDA0003061849950000021
wherein t is the first duration, p is the number of users, m is the number of messages, and w is the wonderful degree of the live broadcast segment of the first duration.
4. The method as claimed in claim 1, wherein the step of selecting a first preset number of live broadcast segments with the highest highlight degree from the live broadcast segments with the first duration to obtain highlight live broadcast segments comprises:
selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration as to-be-processed live broadcast segments;
adding supplementary segments with second time length at the head and tail of each live segment to be processed to obtain a wonderful live segment with third time length;
the third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
5. The method as claimed in claim 1, wherein the step of selecting a first preset number of live broadcast segments with the highest highlight degree from the live broadcast segments with the first duration to obtain highlight live broadcast segments further comprises:
selecting the live broadcast segment with the highest wonderful degree from the live broadcast segments with the first duration as a first live broadcast segment to be processed; adding supplementary segments with second time length at the head and the tail of the first live segment to be processed to obtain a first highlight live segment with third time length;
selecting a next live broadcast segment to be processed meeting a selection rule according to the first highlight live broadcast segment; adding supplementary segments with second time length at the head and tail of the next live segment to be processed to obtain a highlight live segment with third time length;
the currently generated highlight live broadcast segment is always used as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed, and the live broadcast segments with the first duration are traversed according to the selection rule until a second preset number of live broadcast segments to be processed are selected;
the third duration is the sum of the first duration and the second duration; the supplementary segments are live segments without time intervals between the live segments and the head and the tail of each live segment to be processed in live broadcasting;
the selection rule is as follows: and excluding the first highlight live broadcast segment from the live broadcast segments with the first time length, and excluding the live broadcast segments with the fourth time length before and after the first highlight live broadcast segment and without time intervals between the first highlight live broadcast segments, wherein the remaining live broadcast segments with the highest highlight degree in the live broadcast segments with the first time length are the next live broadcast segments to be processed, which meet the selection rule.
6. The method of claim 4 or 5, further comprising:
and when the supplementary segments with the second time length are respectively added at the head and the tail of the live broadcast segment to be processed, if the time length of the supplementary segments is less than the second time length, the live broadcast segment to be processed is dropped.
7. The method as claimed in claim 1, wherein the step of synthesizing the highlight live clips into a live video summary and displaying the live video summary in a live room interface corresponding to a main broadcast comprises:
sorting the highlight live broadcast segments in a descending order according to the highlight degrees of the corresponding live broadcast segments, and synthesizing the highlight live broadcast segments into a current live broadcast video abstract;
and displaying the current live video abstract in a live broadcasting room interface corresponding to the anchor.
8. The method of claim 7, wherein after the step of presenting the current live video summary in a live interface of a corresponding anchor, further comprising:
and playing the current live video abstract according to the sequence that the highlight degree of the highlight live clip corresponding to the highlight live clip is presented from high to low.
9. An apparatus for generating a live video summary, the apparatus comprising:
the live broadcast clip acquisition module is used for acquiring a live broadcast clip with a first duration every other time period from the beginning of live broadcast;
the wonderful degree calculation module is used for acquiring the number of users watching the live broadcast segments of each first time length and the number of messages sent by the users, inputting the acquired number of users and the number of messages into a preset wonderful degree calculation formula, and calculating the wonderful degree of the live broadcast segments of each first time length;
the highlight live broadcast segment acquisition module is used for selecting a first preset number of live broadcast segments with the highest highlight degree from the live broadcast segments with the first time length according to the highlight degree of the live broadcast segments with the first time length to obtain highlight live broadcast segments;
the live broadcast video abstract generating module is used for synthesizing the wonderful live broadcast fragments into a live broadcast video abstract and displaying the live broadcast video abstract in a live broadcast room interface corresponding to the anchor broadcast;
the device also comprises a highlight live broadcast segment updating module, which is specifically used for:
the method comprises the steps that from each new live broadcast, every other time period of first time duration, a live broadcast segment of first time duration corresponding to the new live broadcast, the number of users watching the live broadcast segment and the number of messages sent by the users are obtained, and the wonderness degree of the live broadcast segment in the new live broadcast is calculated by utilizing a preset wonderness degree calculation formula;
comparing the wonderful degree of the live broadcast segments in the new live broadcast with the minimum wonderful degree of the live broadcast segments corresponding to all the wonderful live broadcast segments in the live broadcast video summary displayed currently, and if the wonderful degree of the live broadcast segments in the new live broadcast is greater than the minimum wonderful degree, generating the wonderful live broadcast segments of the live broadcast segments in the new live broadcast;
and updating the highlight live broadcast segment corresponding to the minimum highlight degree in the currently displayed live broadcast video abstract into the highlight live broadcast segment of the live broadcast segment in the new live broadcast.
10. The apparatus of claim 9, wherein the live clip obtaining module is specifically configured to:
acquiring a live broadcast segment with a first duration through continuous sampling; the continuous sampling is that when two adjacent live broadcast segments are obtained within the time period of the first duration, the time interval is 0;
and discarding the last section of live broadcast clip obtained when the live broadcast stops each time.
11. The apparatus of claim 9, wherein the wonderful degree calculation module is specifically configured to:
acquiring the number of users watching the live broadcast segments of each first time length when the live broadcast segments of each first time length are finished;
acquiring the number of messages which are sent by a user and correspond to the live broadcast segments of each first time length within the first time length;
calculating the wonderful degree of each live broadcast segment with the first duration by using a preset wonderful degree calculation formula according to the number of the users and the number of the messages;
the preset wonderful degree calculation formula is as follows:
Figure FDA0003061849950000051
wherein t is the first duration, p is the number of users, m is the number of messages, and w is the wonderful degree of the live broadcast segment of the first duration.
12. The apparatus of claim 9, wherein the highlight live clip obtaining module is specifically configured to:
selecting a first preset number of live broadcast segments with the highest wonderful degree from the live broadcast segments with the first duration as to-be-processed live broadcast segments;
adding supplementary segments with second time length at the head and tail of each live segment to be processed to obtain a wonderful live segment with third time length;
the third duration is the sum of the first duration and the second duration; the supplementary clips are live clips without time intervals between the live clips and the head and the tail of each live clip to be processed in live broadcasting.
13. The apparatus of claim 9, wherein the highlight live clip obtaining module comprises:
the first obtaining submodule is used for selecting the live broadcast segment with the highest wonderful degree from the live broadcast segments with the first duration as a first to-be-processed live broadcast segment; adding supplementary segments with second time length at the head and the tail of the first live segment to be processed to obtain a first highlight live segment with third time length;
the second acquisition submodule is used for selecting the next live broadcast segment to be processed which meets the selection rule according to the first highlight live broadcast segment; adding supplementary segments with second time length at the head and tail of the next live segment to be processed to obtain a highlight live segment with third time length;
the currently generated highlight live broadcast segment is always used as a first highlight live broadcast segment for selecting the next live broadcast segment to be processed, and the live broadcast segments with the first duration are traversed according to the selection rule until a second preset number of live broadcast segments to be processed are selected;
the third duration is the sum of the first duration and the second duration; the supplementary segments are live segments without time intervals between the live segments and the head and the tail of each live segment to be processed in live broadcasting;
the selection rule is as follows: and excluding the first highlight live broadcast segment from the live broadcast segments with the first time length, and excluding the live broadcast segments with the fourth time length before and after the first highlight live broadcast segment and without time intervals between the first highlight live broadcast segments, wherein the remaining live broadcast segments with the highest highlight degree in the live broadcast segments with the first time length are the next live broadcast segments to be processed, which meet the selection rule.
14. The apparatus according to claim 12 or 13, wherein the highlight live section obtaining module is specifically configured to:
and when the supplementary segments with the second time length are respectively added at the head and the tail of the live broadcast segment to be processed, if the time length of the supplementary segments is less than the second time length, the live broadcast segment to be processed is dropped.
15. The apparatus of claim 9, wherein the live video summary generation module is specifically configured to:
sorting the highlight live broadcast segments in a descending order according to the highlight degrees of the corresponding live broadcast segments, and synthesizing the highlight live broadcast segments into a current live broadcast video abstract;
and displaying the current live video abstract in a live broadcasting room interface corresponding to the anchor.
16. The apparatus of claim 15, wherein the live video summary generation module is specifically configured to:
and playing the current live video abstract according to the sequence that the highlight degree of the highlight live clip corresponding to the highlight live clip is presented from high to low.
17. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any of the preceding claims 1 to 8 when executing a program stored in a memory.
CN201711470643.2A 2017-12-29 2017-12-29 Live video abstract generation method and device and electronic equipment Active CN108062409B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711470643.2A CN108062409B (en) 2017-12-29 2017-12-29 Live video abstract generation method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711470643.2A CN108062409B (en) 2017-12-29 2017-12-29 Live video abstract generation method and device and electronic equipment

Publications (2)

Publication Number Publication Date
CN108062409A CN108062409A (en) 2018-05-22
CN108062409B true CN108062409B (en) 2021-06-22

Family

ID=62140839

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711470643.2A Active CN108062409B (en) 2017-12-29 2017-12-29 Live video abstract generation method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN108062409B (en)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108810641A (en) * 2018-06-04 2018-11-13 北京潘达互娱科技有限公司 A kind of video broadcasting method, device and electronic equipment
CN109068150A (en) * 2018-08-07 2018-12-21 深圳市创梦天地科技有限公司 A kind of excellent picture extracting method, terminal and the computer-readable medium of video
CN109120954B (en) * 2018-09-30 2021-09-07 武汉斗鱼网络科技有限公司 Video message pushing method and device, computer equipment and storage medium
CN111343391A (en) * 2018-12-18 2020-06-26 宏碁股份有限公司 Video capture method and electronic device using same
CN109685144B (en) * 2018-12-26 2021-02-12 上海众源网络有限公司 Method and device for evaluating video model and electronic equipment
CN109982109B (en) * 2019-04-03 2021-08-03 睿魔智能科技（深圳）有限公司 Short video generation method and device, server and storage medium
CN110401873A (en) * 2019-06-17 2019-11-01 北京奇艺世纪科技有限公司 Video clipping method, device, electronic equipment and computer-readable medium
CN110797013A (en) * 2019-09-11 2020-02-14 腾讯科技（深圳）有限公司 Live broadcast entrance display method of voice live broadcast room, related equipment and storage medium
CN111182358B (en) * 2019-12-30 2021-09-28 腾讯科技（深圳）有限公司 Video processing method, video playing method, device, equipment and storage medium
CN111400511B (en) * 2020-03-12 2024-06-14 北京奇艺世纪科技有限公司 Method and device for intercepting multimedia resources
JP6748323B1 (en) * 2020-03-30 2020-08-26 株式会社ドワンゴ Movie distribution device, movie distribution method, and movie distribution program
CN111447489A (en) * 2020-04-02 2020-07-24 北京字节跳动网络技术有限公司 Video processing method and device, readable medium and electronic equipment
CN111479168B (en) * 2020-04-14 2021-12-28 腾讯科技（深圳）有限公司 Method, device, server and medium for marking multimedia content hot spot
CN111698575B (en) * 2020-06-19 2022-06-07 广州方硅信息技术有限公司 Live highlight video editing method, device, equipment and storage medium
CN111698554B (en) * 2020-06-19 2022-06-07 广州方硅信息技术有限公司 Live video album generating method, device, equipment and storage medium
CN111918146B (en) * 2020-07-28 2021-06-01 广州筷子信息科技有限公司 Video synthesis method and system
CN111836119A (en) * 2020-07-22 2020-10-27 广州华多网络科技有限公司 Live broadcast wonderful video tracking method, device, equipment and storage medium
CN112637618B (en) * 2020-12-08 2023-09-08 广州博冠信息科技有限公司 Live broadcast playback video generation method and device, electronic equipment and computer medium
CN112822504B (en) * 2020-12-30 2023-07-25 北京达佳互联信息技术有限公司 Live broadcast room cover updating method and device, electronic equipment and storage medium
CN113542801B (en) * 2021-06-29 2023-06-06 北京百度网讯科技有限公司 Method, device, equipment, storage medium and program product for generating anchor identification
CN114189719B (en) * 2021-11-11 2024-04-16 北京达佳互联信息技术有限公司 Video information extraction method and device, electronic equipment and storage medium
CN116962796A (en) * 2023-09-19 2023-10-27 星河视效科技(北京)有限公司 Cross-screen interaction method, device, equipment and medium applied to live broadcast scene

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070266001A1 (en) * 2006-05-09 2007-11-15 Microsoft Corporation Presentation of duplicate and near duplicate search results
CN105787049B (en) * 2016-02-26 2019-07-16 浙江大学 A kind of network video focus incident discovery method based on Multi-source Information Fusion analysis
CN106231379A (en) * 2016-07-29 2016-12-14 广州酷狗计算机科技有限公司 A kind of methods, devices and systems playing live video
CN106792085B (en) * 2016-12-09 2019-11-05 广州华多网络科技有限公司 A kind of method and apparatus generating video cover image
CN107426583B (en) * 2017-06-16 2020-10-16 广州视源电子科技股份有限公司 Video editing method, server and video playing system based on hot spots

Also Published As

Publication number Publication date
CN108062409A (en) 2018-05-22

Similar Documents

Publication Publication Date Title
CN108062409B (en) Live video abstract generation method and device and electronic equipment
US10764619B2 (en) Method and system for providing social media content synchronized to media presentation
US9602886B2 (en) Methods and systems for displaying contextually relevant information from a plurality of users in real-time regarding a media asset
US10841352B2 (en) Non-chronological buffering of segments of a media file
CN109474854B (en) Video playing method, playlist generating method and related equipment
US20170019715A1 (en) Media production system with scheduling feature
US20140267303A1 (en) Animation
US20210160577A1 (en) Method for playing video, electronic device and storage medium
CN104378662B (en) The system and method that a kind of smart television judges the effective viewed programs of user
US10021433B1 (en) Video-production system with social-media features
CN109120954B (en) Video message pushing method and device, computer equipment and storage medium
US11006180B2 (en) Media clipper system
CN111767430B (en) Video resource pushing method, video resource pushing device and storage medium
US11483630B1 (en) Systems and methods to generate metadata for content
US20220272421A1 (en) Content Aggregation
CN103442270A (en) Method and device for acquiring viewing data of user
CN109587517B (en) Multimedia file playing method and device, server and storage medium
US9584572B2 (en) Cloud service device, multi-image preview method and cloud service system
CN108111900B (en) Playing speed control method and device
CN109815408B (en) Method and device for pushing information
CN116844534A (en) Voice recognition method and device
CN118102047A (en) Video processing method, video processing device, electronic equipment and computer readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant