CN113315988A - Live video recommendation method and device - Google Patents
Live video recommendation method and device Download PDFInfo
- Publication number
- CN113315988A CN113315988A CN202110591353.3A CN202110591353A CN113315988A CN 113315988 A CN113315988 A CN 113315988A CN 202110591353 A CN202110591353 A CN 202110591353A CN 113315988 A CN113315988 A CN 113315988A
- Authority
- CN
- China
- Prior art keywords
- user
- live broadcast
- recommendation
- broadcast room
- live
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000006399 behavior Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 5
- 238000002372 labelling Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- 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
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
-
- 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
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/233—Processing of audio elementary streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a live video recommendation method and a live video recommendation device, wherein the method comprises the following steps: when detecting that the live broadcast room is in a live broadcast state, acquiring a video frame and an audio of a live broadcast video of the live broadcast room; carrying out image recognition on a currently acquired video frame; performing voice recognition on the currently acquired audio; judging whether a target label matched with the live broadcast room exists in the alternative label set or not based on the image recognition result and the voice recognition result; if yes, adding a target label to the live broadcast room, and determining a user set corresponding to the target label; the user set comprises users with set target labels; judging whether each user in the user set meets the recommendation condition; and if the users meeting the recommendation conditions exist, recommending the live broadcast video of the live broadcast room for the users meeting the recommendation conditions. By applying the live video recommendation method provided by the invention, the live content which the user is interested in can be recommended for the user, so that the user can be prevented from missing the interested video.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a live video recommendation method and device.
Background
With the development of science and technology, various internet platforms appear in the internet, and the life of people is greatly enriched, for example, a live network platform can provide rich and colorful live network for users, and the entertainment requirements of the users can be met.
However, the webcast platform usually includes multiple types of live rooms, and the live content presented by different live rooms in the live process may be diversified, so that it is difficult for the user to find the live content of interest in the live platform.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a live video recommendation method, which can recommend live content interested by a user.
The invention also provides a live video recommendation device used for ensuring the realization and application of the method in practice.
A live video recommendation method includes:
when detecting that a live broadcast room is in a live broadcast state, acquiring a video frame and an audio of a live broadcast video of the live broadcast room;
performing image recognition on the currently acquired video frame to obtain an image recognition result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio;
judging whether a target label matched with a live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result;
if a target label matched with the live broadcast room exists in the alternative label set, adding the target label to the live broadcast room, and determining a user set corresponding to the target label; the user set comprises users with the target tags set;
judging whether each user in the user set meets preset recommendation conditions or not;
and if the users meeting the recommendation conditions exist in the user set, recommending the live video of the live broadcast room for the users meeting the recommendation conditions.
Optionally, in the foregoing method, the determining, based on each image recognition result and the voice recognition result, whether a target tag matching a live broadcast room exists in a preset candidate tag set includes:
determining the occurrence frequency of a key mark under the condition that the image recognition result represents that the video frame comprises the preset key mark; determining a first weight value of the key mark based on the occurrence frequency of the key mark;
determining the occurrence frequency of a keyword under the condition that the audio recognition result comprises the preset keyword; determining a second weight value of the keyword based on the occurrence frequency of the keyword;
determining a first alternative label associated with the key mark and a second alternative label associated with the key word in the alternative label set;
judging whether the first weight value is greater than or equal to a first weight threshold of the first alternative label or not to obtain a first judgment result; judging whether the second weight value is greater than or equal to a second weight threshold of the second alternative label or not to obtain a second judgment result;
if at least one of the first judgment result and the second judgment result is yes, determining that a target label matched with the live broadcast room exists in the alternative label set;
and if the first judgment result and the second judgment result are both negative, determining that no target label matched with the live broadcast room exists in the alternative label set.
Optionally, the method described above, where the process of setting the target tag for the user includes:
acquiring behavior data of the user associated with the target tag;
determining a tag weight value for the user based on the behavior data; the label weight value represents the interest degree of the user in the target label;
and setting the target label for the user under the condition that the label weight value of the user is greater than a preset third weight threshold value.
Optionally, the method for determining whether each user in the user set meets a preset recommendation condition includes:
for each user in the user set, judging whether live video of the live broadcast room is recommended to the user in the current time period, if the live video of the live broadcast room is not recommended to the user in the current time period, acquiring the recommendation times of the target user in the current time period, judging whether the recommendation times are greater than a preset recommendation time threshold value, and if the recommendation times are not greater than the recommendation time threshold value, determining that the user meets the recommendation condition; and if the recommendation times are larger than the recommendation time threshold value, or the live videos among the indexes are recommended to the user in the current time period, determining that the user does not meet the recommendation conditions.
Optionally, the recommending the live video of the live broadcast room for the user meeting the recommendation condition includes:
acquiring the residual live broadcast time length of the live broadcast room;
if the residual live broadcast time length is greater than or equal to a preset time length threshold value, generating a push message of the live broadcast room, and sending the push message to the user meeting the recommendation condition so as to recommend the live broadcast video of the live broadcast room to the user meeting the recommendation condition;
if the residual live broadcast time length is smaller than the time length threshold value, when the live broadcast video of the live broadcast room enters a playback state, a push message of the live broadcast video is generated and sent to the users meeting the recommendation condition, so that the live broadcast video of the live broadcast room is recommended to the users meeting the recommendation condition.
A live video recommendation apparatus comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a video frame and an audio of a live video of a live broadcast room when detecting that the live broadcast room is in a live broadcast state;
the identification unit is used for carrying out image identification on the currently acquired video frame to obtain an image identification result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio;
the first judgment unit is used for judging whether a target label matched with a live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result;
a determining unit, configured to add a target tag to the live broadcast room if the target tag matched with the live broadcast room exists in the alternative tag set, and determine a user set corresponding to the target tag; the user set comprises users with the target tags set;
the second judging unit is used for judging whether each user in the user set meets preset recommendation conditions or not;
and the recommending unit is used for recommending the live video of the live broadcast room for the user meeting the recommending condition if the user meeting the recommending condition exists in the user set.
Optionally, the apparatus described above, wherein the first determining unit includes:
the first determining subunit is used for determining the occurrence frequency of a key mark under the condition that the image recognition result represents that the video frame comprises the preset key mark; determining a first weight value of the key mark based on the occurrence frequency of the key mark;
a second determining subunit, configured to determine an occurrence frequency of a keyword when the audio recognition result includes the preset keyword; determining a second weight value of the keyword based on the occurrence frequency of the keyword;
a third determining subunit, configured to determine, in the alternative tag set, a first alternative tag associated with the key token and a second alternative tag associated with the keyword;
the judging subunit is configured to judge whether the first weight value is greater than or equal to a first weight threshold of the first alternative tag, so as to obtain a first judgment result; judging whether the second weight value is greater than or equal to a second weight threshold of the second alternative label or not to obtain a second judgment result;
a fourth determining subunit, configured to determine that a target tag matching the live broadcast room exists in the alternative tag set if at least one of the first determination result and the second determination result is yes;
a fifth determining subunit, configured to determine that a target tag that is matched with the live broadcast room does not exist in the alternative tag set if both the first determination result and the second determination result are negative.
The above apparatus, optionally, the determining unit includes:
the first acquisition subunit is used for acquiring behavior data of the user, which is associated with the target tag;
a sixth determining subunit, configured to determine a tag weight value of the user based on the behavior data; the label weight value represents the interest degree of the user in the target label;
and the setting subunit is configured to set the target tag for the user when the tag weight value of the user is greater than a preset third weight threshold.
The above apparatus, optionally, the second determining unit includes:
the execution subunit is configured to, for each user in the user set, determine whether a live video of the live broadcast room has been recommended to the user in a current time period, if the live video of the live broadcast room has not been recommended to the user in the current time period, obtain recommendation times of the target user in the current time period, determine whether the recommendation times are greater than a preset recommendation time threshold, and if the recommendation times are not greater than the recommendation time threshold, determine that the user meets the recommendation condition; and if the recommendation times are larger than the recommendation time threshold value, or the live videos among the indexes are recommended to the user in the current time period, determining that the user does not meet the recommendation conditions.
The above apparatus, optionally, the recommending unit includes:
the second acquisition subunit is used for acquiring the residual live broadcast time length of the live broadcast room;
the first generation subunit is configured to generate a push message of the live broadcast room if the remaining live broadcast time length is greater than or equal to a preset time length threshold, and send the push message to a user who meets the recommendation condition, so as to recommend a live broadcast video of the live broadcast room to the user who meets the recommendation condition;
and the second generation subunit is used for generating a push message of the live video when the live video of the live broadcast room enters a playback state if the residual live broadcast time length is less than the time length threshold value, and sending the push message to the user meeting the recommendation condition so as to recommend the live video of the live broadcast room to the user meeting the recommendation condition.
A storage medium comprising stored instructions, wherein the instructions, when executed, control a device on which the storage medium is located to perform a live video recommendation method as described above.
An electronic device comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform a live video recommendation method as described above.
Compared with the prior art, the invention has the following advantages:
the invention provides a live video recommendation method and a live video recommendation device, wherein the method comprises the following steps: when detecting that a live broadcast room is in a live broadcast state, acquiring a video frame and an audio of a live broadcast video of the live broadcast room; performing image recognition on the currently acquired video frame to obtain an image recognition result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio; judging whether a target label matched with a live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result; if a target label matched with the live broadcast room exists in the alternative label set, adding the target label to the live broadcast room, and determining a user set corresponding to the target label; the user set comprises users with the target tags set; judging whether each user in the user set meets preset recommendation conditions or not; and if the users meeting the recommendation conditions exist in the user set, recommending the live video of the live broadcast room for the users meeting the recommendation conditions. By applying the live video recommendation method provided by the invention, the live content which the user is interested in can be recommended for the user, so that the user can be prevented from missing the interested video, and the live watching experience of the user is improved.
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, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for recommending a live video according to the present invention;
fig. 2 is a flowchart of a process of determining whether a target tag matching a live broadcast room exists in an alternative tag set according to the present invention;
FIG. 3 is a flow chart of a process for setting a target tag for a user according to the present invention;
FIG. 4 is a flowchart of a process for recommending live video of a live broadcast room for a user meeting a recommendation condition according to the present invention;
FIG. 5 is a flow chart of a process for setting a tag for a user according to the present invention;
fig. 6 is a flowchart of another method of a live video recommendation method according to the present invention;
fig. 7 is a schematic structural diagram of a live video recommendation apparatus according to the present invention;
fig. 8 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In this application, 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.
The embodiment of the invention provides a live video recommendation method, which can be applied to electronic equipment, wherein the method has a flow chart as shown in fig. 1, and specifically comprises the following steps:
s101: and when detecting that the live broadcast room is in a live broadcast state, acquiring a video frame and audio of a live broadcast video of the live broadcast room.
In the embodiment of the invention, the live broadcast state of the live broadcast room can be detected, and when the live broadcast room is detected to be in the live broadcast state, the video frame and the audio of the live broadcast video of the live broadcast room can be acquired in real time.
The live video may include a video frame and an audio, the video frame may be a video frame currently played, the audio may be an audio of a preset time period, and the time period includes a current time.
S102: performing image recognition on the currently acquired video frame to obtain an image recognition result of the video frame; and performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio.
In the embodiment of the present invention, a feasible way of performing image recognition on a currently acquired video frame includes: preprocessing the video frame, inputting the preprocessed video frame into a preset image recognition model, and obtaining an image recognition result of the video frame; the preprocessing of the video frame may include denoising the video frame, and the process of obtaining the denoising of the video frame may include image sampling, image enhancement, image restoration, image encoding and compression, and image segmentation.
In the embodiment of the present invention, a feasible way of performing speech recognition on currently acquired audio includes: and preprocessing the audio, inputting the preprocessed audio into a pre-constructed voice recognition model, and obtaining a voice recognition result of the audio, wherein the voice recognition result can be text information.
S103: and judging whether a target label matched with the live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result.
In an embodiment of the present invention, the alternative tab set includes alternative tabs that have not been added to the live broadcast.
S104: if a target label matched with the live broadcast room exists in the alternative label set, adding the target label to the live broadcast room, and determining a user set corresponding to the target label; the user set comprises users which are set with the target tags.
In the embodiment of the present invention, the target tag is a candidate tag matched with the live broadcast room in the candidate tag set, and each candidate tag in the candidate tag set has its corresponding user set.
And for the user set corresponding to the target label, at least setting the target label for each user in the user set.
If the target tag matched with the live broadcast room does not exist in the alternative tag set, detecting the live broadcast state of the live broadcast, and if the target tag is in the live broadcast state, returning to execute the step S101.
S105: and judging whether each user in the user set meets preset recommendation conditions.
In the embodiment of the present invention, the recommendation condition may be that the user has not recommended the live video in the live broadcast room in the current time period, and the recommendation frequency in the current time period is less than a set frequency threshold.
S106: and if the users meeting the recommendation conditions exist in the user set, recommending the live video of the live broadcast room for the users meeting the recommendation conditions.
In the embodiment of the present invention, the live video currently live broadcast can be recommended to the user meeting the recommendation condition, and after the live broadcast is finished, the live video is in a playable state, and the live video in a playable state is recommended to the user, so that the user can be prevented from missing the content of interest of the user.
By applying the live video recommendation method provided by the invention, the live content which the user is interested in can be provided for the user, the user can be prevented from missing the interested video, and the user experience is improved.
In this embodiment of the present invention, based on the foregoing implementation process, specifically, the determining, based on each image recognition result and the voice recognition result, whether a target tag matching a live broadcast exists in a preset candidate tag set, as shown in fig. 2, includes:
s201: determining the occurrence frequency of a key mark under the condition that the image recognition result represents that the video frame comprises the preset key mark; determining a first weight value of the key indicator based on the frequency of occurrence of the key indicator.
In the embodiment of the invention, the key mark can be included marks in various live scenes such as dances, podcasts, props, buildings, furniture and the like.
Specifically, the number of the key marks included in the video frame may be one or more, and the cumulative occurrence number and the time of each occurrence of each key mark may be determined, so as to determine the occurrence frequency of each key mark.
The occurrence frequency of the key mark is calculated in a preset calculation mode, and a first weight value of the key mark is obtained, wherein the higher the occurrence frequency of the key mark is, the larger the first weight value is.
S202: determining the occurrence frequency of a keyword under the condition that the audio recognition result comprises the preset keyword; determining a second weight value of the keyword based on the frequency of occurrence of the keyword.
In the embodiment of the present invention, the audio recognition result may be text information, the audio recognition result may include one or more keywords, and the cumulative occurrence number and the time of each occurrence of each keyword may be determined, so as to determine the occurrence frequency of each keyword.
And calculating the occurrence frequency of the keyword in a preset calculation mode to obtain a second weight value of the key mark, wherein the higher the occurrence frequency of the keyword is, the larger the second weight value is.
S203: determining a first alternative label associated with the key token and a second alternative label associated with the keyword in the set of alternative labels.
The alternative labels associated with the key marks in the alternative label set are used as first alternative labels, and the alternative labels associated with each key mark are one or more; and taking the alternative labels associated with the keywords in the alternative label set as second alternative labels, wherein the alternative labels associated with each keyword can be one or more.
In the embodiment of the present invention, each alternative tag in the alternative tag set may have an association relationship with at least one key mark and a keyword.
S204: judging whether the first weight value is greater than or equal to a first weight threshold of the first alternative label or not to obtain a first judgment result; and judging whether the second weight value is greater than or equal to a second weight threshold of the second alternative label to obtain a second judgment result.
In embodiments of the present invention, the weight threshold for each alternative tag may be the same or different.
S205: and if at least one of the first judgment result and the second judgment result is yes, determining that a target label matched with the live broadcast room exists in the alternative label set.
In this embodiment of the present invention, the number of target tags may be one or more, specifically, if the first weight value is greater than or equal to the first weight threshold, the first candidate tag may be regarded as the target tag, and if the second weight value is greater than or equal to the second weight threshold, the second candidate representation may be regarded as the target tag.
S206: and if the first judgment result and the second judgment result are both negative, determining that no target label matched with the live broadcast room exists in the alternative label set.
In the embodiment of the present invention, under the condition that it is determined that no target tag matching with the live broadcast room exists in the candidate tag set, the live broadcast state of the live broadcast may be detected, and if the target tag is in the live broadcast state, S101 may be executed in a return manner.
In the embodiment of the present invention, based on the implementation process, specifically, the feasible manner for setting the target tag for the user specifically includes, as shown in fig. 3:
s301: and acquiring behavior data of the user, which is associated with the target label.
The behavior data of the user can be acquired in the process that the user watches the video carrying the target tag, and the behavior data may include: the method comprises the following steps of one or more of a main broadcast concerned by a user, a user appreciation condition, user and main broadcast interactive content, a user purchasing a live broadcast recommended product, a live broadcast watching time length, a user watching playback frequency and time length, a type of a red envelope and a coupon received by the user, a type of participation activity and the like.
S302: determining a tag weight value for the user based on the behavior data; the tag weight value characterizes a degree of interest of the user in the target tag.
S303: and setting the target label for the user under the condition that the label weight value of the user is greater than a preset third weight threshold value.
In the embodiment of the present invention, another feasible way for setting a target tag for a user may be: and responding to the selection operation of the user to the label icon corresponding to the target label when the user enters the platform, and setting the target label for the user.
Yet another possible way to set the target tag for the user may be: the frequency of live broadcast corresponding to the target label searched by the user according to the classification can be determined, and the label is set for the user under the condition that the frequency meets the preset size.
Yet another possible way to set the target tag for the user may be: and setting the target label for the user under the condition that the user pays attention to the anchor with the target label.
In this embodiment of the present invention, based on the foregoing implementation process, specifically, the determining whether each user in the user set meets a preset recommendation condition includes:
for each user in the user set, judging whether live video of the live broadcast room is recommended to the user in the current time period, if the live video of the live broadcast room is not recommended to the user in the current time period, acquiring the recommendation times of the target user in the current time period, judging whether the recommendation times are greater than a preset recommendation time threshold value, and if the recommendation times are not greater than the recommendation time threshold value, determining that the user meets the recommendation condition; and if the recommendation times are larger than the recommendation time threshold value, or the live videos among the indexes are recommended to the user in the current time period, determining that the user does not meet the recommendation conditions.
In this embodiment of the present invention, based on the foregoing implementation process, specifically, the recommending a live video of the live broadcast room for a user who meets the recommendation condition includes, as shown in fig. 4:
s401: and acquiring the residual live broadcast time length of the live broadcast room.
S402: and if the residual live broadcast time length is greater than or equal to a preset time length threshold value, generating a push message of the live broadcast room, and sending the push message to the user meeting the recommendation condition so as to recommend the live broadcast video of the live broadcast room to the user meeting the recommendation condition.
S403: if the residual live broadcast time length is smaller than the time length threshold value, when the live broadcast video of the live broadcast room enters a playback state, a push message of the live broadcast video is generated and sent to the users meeting the recommendation condition, so that the live broadcast video of the live broadcast room is recommended to the users meeting the recommendation condition.
In the embodiment of the present invention, when a live video enters a playback state, a user may also set a tag for the user while watching the live video in the playback state, as shown in fig. 5, for a flowchart of a process of setting a tag for a user provided by the embodiment of the present invention, according to whether to pay attention to a anchor, if the anchor is paid attention to, the tag of the anchor itself may be extracted; purchasing show window commodities, and extracting commodity labels, wherein the label weight is highest; the live broadcast watching duration represents the degree of the user who likes the live broadcast, and whether the user is uninteresting or very interested is determined; participating in activities and getting the red pack coupons, users have requirements on activity representatives, and the weight can be slightly higher; and abstracting the label according to the label obtained by the conditions and the weight of the label, and labeling the user.
In an embodiment provided by the present invention, when a live video is in a live state, a live video is analyzed, identified, and pushed, referring to fig. 6, a flowchart of another method of a live video recommendation method provided for implementation of the present invention may include two parts:
the first part is: the method comprises the steps of recognizing voice and images, adding live broadcast marks, pushing, converting voice into characters, extracting keywords and the occurrence frequency of the keywords from the characters, setting weights according to the frequency, and adding labels to live broadcasts after the weights are increased to a threshold value; capturing frames by frames in the live broadcast, eliminating repeated frames, analyzing marks and occurrence frequency in the frames, setting weight according to the frequency, and adding a label to the live broadcast when the weight is increased to a threshold value; when a new label appears in the live broadcast, all users below the label are searched, the users need to meet two conditions that the users are not pushed by the live broadcast and are not watching the live broadcast, and the users are pushed to the users after being inquired.
The second part is as follows: and analyzing the user behavior in the observation, and labeling the user. According to whether the anchor is concerned, if the anchor is concerned, the label of the anchor can be extracted; purchasing show window commodities, and extracting commodity labels, wherein the label weight is highest; whether the user has a reward or not needs to actively pay actions and money for reward, the reward is very interesting, and the label weight is high; chatting content, extracting key words; the live broadcast watching duration represents the degree of the user who likes the live broadcast, and whether the user is uninteresting or very interested is determined; participating in activities and getting the red pack coupons, users have requirements on activity representatives, and the weight can be slightly higher; and abstracting the label according to the label obtained by the conditions and the weight of the label, and labeling the user.
Corresponding to the method illustrated in fig. 1, an embodiment of the present invention further provides a live video recommendation apparatus, which is used for specifically implementing the method illustrated in fig. 1, where the live video recommendation apparatus provided in the embodiment of the present invention may be applied to an electronic device, and a schematic structural diagram of the live video recommendation apparatus is illustrated in fig. 7, and specifically includes:
an obtaining unit 701, configured to obtain a video frame and an audio of a live video in a live broadcast room when it is detected that the live broadcast room is in a live broadcast state;
an identifying unit 702, configured to perform image identification on the currently acquired video frame, so as to obtain an image identification result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio;
a first determining unit 703, configured to determine, based on the image recognition result and the voice recognition result, whether a target tag matching a live broadcast room exists in a preset candidate tag set;
a determining unit 704, configured to add a target tag to the live broadcast room if the target tag matched with the live broadcast room exists in the alternative tag set, and determine a user set corresponding to the target tag; the user set comprises users with the target tags set;
a second determining unit 705, configured to determine whether each user in the user set meets a preset recommendation condition;
a recommending unit 706, configured to recommend the live video of the live broadcast room for a user who meets the recommendation condition if the user who meets the recommendation condition exists in the user set.
In an embodiment of the present invention, based on the above scheme, optionally, the first determining unit 703 includes:
the first determining subunit is used for determining the occurrence frequency of a key mark under the condition that the image recognition result represents that the video frame comprises the preset key mark; determining a first weight value of the key mark based on the occurrence frequency of the key mark;
a second determining subunit, configured to determine an occurrence frequency of a keyword when the audio recognition result includes the preset keyword; determining a second weight value of the keyword based on the occurrence frequency of the keyword;
a third determining subunit, configured to determine, in the alternative tag set, a first alternative tag associated with the key token and a second alternative tag associated with the keyword;
the judging subunit is configured to judge whether the first weight value is greater than or equal to a first weight threshold of the first alternative tag, so as to obtain a first judgment result; judging whether the second weight value is greater than or equal to a second weight threshold of the second alternative label or not to obtain a second judgment result;
a fourth determining subunit, configured to determine that a target tag matching the live broadcast room exists in the alternative tag set if at least one of the first determination result and the second determination result is yes;
a fifth determining subunit, configured to determine that a target tag that is matched with the live broadcast room does not exist in the alternative tag set if both the first determination result and the second determination result are negative.
In an embodiment provided by the present invention, based on the above scheme, optionally, the determining unit 704 includes:
the first acquisition subunit is used for acquiring behavior data of the user, which is associated with the target tag;
a sixth determining subunit, configured to determine a tag weight value of the user based on the behavior data; the label weight value represents the interest degree of the user in the target label;
and the setting subunit is configured to set the target tag for the user when the tag weight value of the user is greater than a preset third weight threshold.
In an embodiment of the present invention, based on the above scheme, optionally, the second determining unit 705 includes:
the execution subunit is configured to, for each user in the user set, determine whether a live video of the live broadcast room has been recommended to the user in a current time period, if the live video of the live broadcast room has not been recommended to the user in the current time period, obtain recommendation times of the target user in the current time period, determine whether the recommendation times are greater than a preset recommendation time threshold, and if the recommendation times are not greater than the recommendation time threshold, determine that the user meets the recommendation condition; and if the recommendation times are larger than the recommendation time threshold value, or the live videos among the indexes are recommended to the user in the current time period, determining that the user does not meet the recommendation conditions.
In an embodiment provided by the present invention, based on the above scheme, optionally, the recommending unit 706 includes:
the second acquisition subunit is used for acquiring the residual live broadcast time length of the live broadcast room;
the first generation subunit is configured to generate a push message of the live broadcast room if the remaining live broadcast time length is greater than or equal to a preset time length threshold, and send the push message to a user who meets the recommendation condition, so as to recommend a live broadcast video of the live broadcast room to the user who meets the recommendation condition;
and the second generation subunit is used for generating a push message of the live video when the live video of the live broadcast room enters a playback state if the residual live broadcast time length is less than the time length threshold value, and sending the push message to the user meeting the recommendation condition so as to recommend the live video of the live broadcast room to the user meeting the recommendation condition.
The specific principle and the execution process of each unit and each module in the live video recommendation device disclosed in the embodiment of the present invention are the same as those of the live video recommendation method disclosed in the embodiment of the present invention, and reference may be made to corresponding parts in the live video recommendation method provided in the embodiment of the present invention, which are not described herein again.
The embodiment of the invention also provides a storage medium, which comprises a stored instruction, wherein when the instruction runs, the device where the storage medium is located is controlled to execute the live video recommendation method.
An electronic device is provided in an embodiment of the present invention, and the structural diagram of the electronic device is shown in fig. 8, which specifically includes a memory 801 and one or more instructions 802, where the one or more instructions 802 are stored in the memory 801 and configured to be executed by the one or more processors 803 to perform the following operations:
when detecting that a live broadcast room is in a live broadcast state, acquiring a video frame and an audio of a live broadcast video of the live broadcast room;
performing image recognition on the currently acquired video frame to obtain an image recognition result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio;
judging whether a target label matched with a live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result;
if a target label matched with the live broadcast room exists in the alternative label set, adding the target label to the live broadcast room, and determining a user set corresponding to the target label; the user set comprises users with the target tags set;
judging whether each user in the user set meets preset recommendation conditions or not;
and if the users meeting the recommendation conditions exist in the user set, recommending the live video of the live broadcast room for the users meeting the recommendation conditions.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Finally, it should also be 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.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in a plurality of software and/or hardware when implementing the invention.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The live video recommendation method provided by the invention is described in detail above, and the principle and the implementation mode of the invention are explained by applying a specific example, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A live video recommendation method is characterized by comprising the following steps:
when detecting that a live broadcast room is in a live broadcast state, acquiring a video frame and an audio of a live broadcast video of the live broadcast room;
performing image recognition on the currently acquired video frame to obtain an image recognition result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio;
judging whether a target label matched with a live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result;
if a target label matched with the live broadcast room exists in the alternative label set, adding the target label to the live broadcast room, and determining a user set corresponding to the target label; the user set comprises users with the target tags set;
judging whether each user in the user set meets preset recommendation conditions or not;
and if the users meeting the recommendation conditions exist in the user set, recommending the live video of the live broadcast room for the users meeting the recommendation conditions.
2. The method according to claim 1, wherein the determining whether a target tag matching a live broadcast exists in a preset candidate tag set based on each of the image recognition result and the voice recognition result comprises:
determining the occurrence frequency of a key mark under the condition that the image recognition result represents that the video frame comprises the preset key mark; determining a first weight value of the key mark based on the occurrence frequency of the key mark;
determining the occurrence frequency of a keyword under the condition that the audio recognition result comprises the preset keyword; determining a second weight value of the keyword based on the occurrence frequency of the keyword;
determining a first alternative label associated with the key mark and a second alternative label associated with the key word in the alternative label set;
judging whether the first weight value is greater than or equal to a first weight threshold of the first alternative label or not to obtain a first judgment result; judging whether the second weight value is greater than or equal to a second weight threshold of the second alternative label or not to obtain a second judgment result;
if at least one of the first judgment result and the second judgment result is yes, determining that a target label matched with the live broadcast room exists in the alternative label set;
and if the first judgment result and the second judgment result are both negative, determining that no target label matched with the live broadcast room exists in the alternative label set.
3. The method of claim 1, wherein the process of setting the target tag for the user comprises:
acquiring behavior data of the user associated with the target tag;
determining a tag weight value for the user based on the behavior data; the label weight value represents the interest degree of the user in the target label;
and setting the target label for the user under the condition that the label weight value of the user is greater than a preset third weight threshold value.
4. The method according to claim 1, wherein the determining whether each of the users in the user set meets a preset recommendation condition comprises:
for each user in the user set, judging whether live video of the live broadcast room is recommended to the user in the current time period, if the live video of the live broadcast room is not recommended to the user in the current time period, acquiring the recommendation times of the target user in the current time period, judging whether the recommendation times are greater than a preset recommendation time threshold value, and if the recommendation times are not greater than the recommendation time threshold value, determining that the user meets the recommendation condition; and if the recommendation times are larger than the recommendation time threshold value, or the live videos among the indexes are recommended to the user in the current time period, determining that the user does not meet the recommendation conditions.
5. The method of claim 1, wherein recommending the live video of the live broadcast room for the user meeting the recommendation condition comprises:
acquiring the residual live broadcast time length of the live broadcast room;
if the residual live broadcast time length is greater than or equal to a preset time length threshold value, generating a push message of the live broadcast room, and sending the push message to the user meeting the recommendation condition so as to recommend the live broadcast video of the live broadcast room to the user meeting the recommendation condition;
if the residual live broadcast time length is smaller than the time length threshold value, when the live broadcast video of the live broadcast room enters a playback state, a push message of the live broadcast video is generated and sent to the users meeting the recommendation condition, so that the live broadcast video of the live broadcast room is recommended to the users meeting the recommendation condition.
6. A live video recommendation apparatus, comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring a video frame and an audio of a live video of a live broadcast room when detecting that the live broadcast room is in a live broadcast state;
the identification unit is used for carrying out image identification on the currently acquired video frame to obtain an image identification result of the video frame; performing voice recognition on the currently acquired audio to acquire a voice recognition result of the audio;
the first judgment unit is used for judging whether a target label matched with a live broadcast room exists in a preset alternative label set or not based on the image recognition result and the voice recognition result;
a determining unit, configured to add a target tag to the live broadcast room if the target tag matched with the live broadcast room exists in the alternative tag set, and determine a user set corresponding to the target tag; the user set comprises users with the target tags set;
the second judging unit is used for judging whether each user in the user set meets preset recommendation conditions or not;
and the recommending unit is used for recommending the live video of the live broadcast room for the user meeting the recommending condition if the user meeting the recommending condition exists in the user set.
7. The apparatus according to claim 6, wherein the first determining unit comprises:
the first determining subunit is used for determining the occurrence frequency of a key mark under the condition that the image recognition result represents that the video frame comprises the preset key mark; determining a first weight value of the key mark based on the occurrence frequency of the key mark;
a second determining subunit, configured to determine an occurrence frequency of a keyword when the audio recognition result includes the preset keyword; determining a second weight value of the keyword based on the occurrence frequency of the keyword;
a third determining subunit, configured to determine, in the alternative tag set, a first alternative tag associated with the key token and a second alternative tag associated with the keyword;
the judging subunit is configured to judge whether the first weight value is greater than or equal to a first weight threshold of the first alternative tag, so as to obtain a first judgment result; judging whether the second weight value is greater than or equal to a second weight threshold of the second alternative label or not to obtain a second judgment result;
a fourth determining subunit, configured to determine that a target tag matching the live broadcast room exists in the alternative tag set if at least one of the first determination result and the second determination result is yes;
a fifth determining subunit, configured to determine that a target tag that is matched with the live broadcast room does not exist in the alternative tag set if both the first determination result and the second determination result are negative.
8. The apparatus of claim 6, wherein the determining unit comprises:
the first acquisition subunit is used for acquiring behavior data of the user, which is associated with the target tag;
a sixth determining subunit, configured to determine a tag weight value of the user based on the behavior data; the label weight value represents the interest degree of the user in the target label;
and the setting subunit is configured to set the target tag for the user when the tag weight value of the user is greater than a preset third weight threshold.
9. The apparatus of claim 6, wherein the second determining unit comprises:
the execution subunit is configured to, for each user in the user set, determine whether a live video of the live broadcast room has been recommended to the user in a current time period, if the live video of the live broadcast room has not been recommended to the user in the current time period, obtain recommendation times of the target user in the current time period, determine whether the recommendation times are greater than a preset recommendation time threshold, and if the recommendation times are not greater than the recommendation time threshold, determine that the user meets the recommendation condition; and if the recommendation times are larger than the recommendation time threshold value, or the live videos among the indexes are recommended to the user in the current time period, determining that the user does not meet the recommendation conditions.
10. The apparatus of claim 6, wherein the recommending unit comprises:
the second acquisition subunit is used for acquiring the residual live broadcast time length of the live broadcast room;
the first generation subunit is configured to generate a push message of the live broadcast room if the remaining live broadcast time length is greater than or equal to a preset time length threshold, and send the push message to a user who meets the recommendation condition, so as to recommend a live broadcast video of the live broadcast room to the user who meets the recommendation condition;
and the second generation subunit is used for generating a push message of the live video when the live video of the live broadcast room enters a playback state if the residual live broadcast time length is less than the time length threshold value, and sending the push message to the user meeting the recommendation condition so as to recommend the live video of the live broadcast room to the user meeting the recommendation condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110591353.3A CN113315988B (en) | 2021-05-28 | 2021-05-28 | Live video recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110591353.3A CN113315988B (en) | 2021-05-28 | 2021-05-28 | Live video recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113315988A true CN113315988A (en) | 2021-08-27 |
| CN113315988B CN113315988B (en) | 2023-04-07 |
Family
ID=77375908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110591353.3A Active CN113315988B (en) | 2021-05-28 | 2021-05-28 | Live video recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113315988B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113727136A (en) * | 2021-09-30 | 2021-11-30 | 广州方硅信息技术有限公司 | Live broadcast pushing method, system, device, equipment and storage medium |
| CN114430503A (en) * | 2022-01-25 | 2022-05-03 | 上海影宴数码科技有限公司 | Big data superposition recommendation method based on short video |
| CN115065837A (en) * | 2022-05-13 | 2022-09-16 | 咪咕视讯科技有限公司 | Video insertion method, device and equipment and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108519991A (en) * | 2018-02-28 | 2018-09-11 | 北京奇艺世纪科技有限公司 | A kind of method and apparatus of main broadcaster's account recommendation |
| CN109151500A (en) * | 2018-09-29 | 2019-01-04 | 北京数美时代科技有限公司 | A kind of main broadcaster's recommended method, system and computer equipment for net cast |
| CN111353068A (en) * | 2020-02-28 | 2020-06-30 | 腾讯音乐娱乐科技（深圳）有限公司 | Video recommendation method and device |
| US20210006864A1 (en) * | 2018-05-28 | 2021-01-07 | Guangzhou Huya Information Technology Co., Ltd. | Method for displaying live broadcast room, apparatus, device, and storage medium |
| CN112528150A (en) * | 2020-12-17 | 2021-03-19 | Oppo广东移动通信有限公司 | Live broadcast recommendation method and device, electronic equipment and storage medium |
-
2021
- 2021-05-28 CN CN202110591353.3A patent/CN113315988B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108519991A (en) * | 2018-02-28 | 2018-09-11 | 北京奇艺世纪科技有限公司 | A kind of method and apparatus of main broadcaster's account recommendation |
| US20210006864A1 (en) * | 2018-05-28 | 2021-01-07 | Guangzhou Huya Information Technology Co., Ltd. | Method for displaying live broadcast room, apparatus, device, and storage medium |
| CN109151500A (en) * | 2018-09-29 | 2019-01-04 | 北京数美时代科技有限公司 | A kind of main broadcaster's recommended method, system and computer equipment for net cast |
| CN111353068A (en) * | 2020-02-28 | 2020-06-30 | 腾讯音乐娱乐科技（深圳）有限公司 | Video recommendation method and device |
| CN112528150A (en) * | 2020-12-17 | 2021-03-19 | Oppo广东移动通信有限公司 | Live broadcast recommendation method and device, electronic equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113727136A (en) * | 2021-09-30 | 2021-11-30 | 广州方硅信息技术有限公司 | Live broadcast pushing method, system, device, equipment and storage medium |
| CN114430503A (en) * | 2022-01-25 | 2022-05-03 | 上海影宴数码科技有限公司 | Big data superposition recommendation method based on short video |
| CN114430503B (en) * | 2022-01-25 | 2023-08-04 | 上海影宴数码科技有限公司 | Short video-based big data superposition recommendation method |
| CN115065837A (en) * | 2022-05-13 | 2022-09-16 | 咪咕视讯科技有限公司 | Video insertion method, device and equipment and computer readable storage medium |
| CN115065837B (en) * | 2022-05-13 | 2023-10-17 | 咪咕视讯科技有限公司 | Video inter-cut method, device, equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113315988B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113315988B (en) | Live video recommendation method and device | |
| CN111143610B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN107870896B (en) | Conversation analysis method and device | |
| US8521818B2 (en) | Methods and apparatus for recognizing and acting upon user intentions expressed in on-line conversations and similar environments | |
| JP5795580B2 (en) | Estimating and displaying social interests in time-based media | |
| CN112399258B (en) | Live playback video generation playing method and device, storage medium and electronic equipment | |
| US20130325992A1 (en) | Methods and apparatus for determining outcomes of on-line conversations and similar discourses through analysis of expressions of sentiment during the conversations | |
| CN112818674A (en) | Live broadcast information processing method, device, equipment and medium | |
| CN108509611B (en) | Method and device for pushing information | |
| CN102216945B (en) | Networking with media fingerprints | |
| CN106503907B (en) | Service evaluation information determination method and server | |
| CN112184290A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| CN111050191B (en) | Video generation method and device, computer equipment and storage medium | |
| CN111931073B (en) | Content pushing method and device, electronic equipment and computer readable medium | |
| EP3031030A1 (en) | Methods and apparatus for determining outcomes of on-line conversations and similar discourses through analysis of expressions of sentiment during the conversations | |
| CN112073738B (en) | Information processing method and device | |
| CN113055751A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN106960033B (en) | Method and device for labeling information stream | |
| CN114881685A (en) | Advertisement delivery method, device, electronic device and storage medium | |
| KR101486924B1 (en) | Method for recommanding media contents using social network service | |
| WO2019199989A1 (en) | Deep neural networks modeling | |
| CN114501163A (en) | Video processing method, device and storage medium | |
| CN113821627A (en) | Neural network, method, device and program for predicting IP work index | |
| CN115134652B (en) | Video dynamic subtitle generation method and device, electronic equipment and storage medium | |
| CN114071176A (en) | Method and device for generating room dynamic information of live broadcast room |
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 |