CN107463552A - A kind of method and apparatus for generating video subject title - Google Patents
A kind of method and apparatus for generating video subject title Download PDFInfo
- Publication number
- CN107463552A CN107463552A CN201710594407.5A CN201710594407A CN107463552A CN 107463552 A CN107463552 A CN 107463552A CN 201710594407 A CN201710594407 A CN 201710594407A CN 107463552 A CN107463552 A CN 107463552A
- Authority
- CN
- China
- Prior art keywords
- word
- video
- descriptor
- subject name
- target
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiments of the invention provide a kind of method and apparatus for generating video subject title, methods described includes：Obtain pre-set text information corresponding to video；Cutting word processing is carried out to the pre-set text information, and using cutting word result as multiple target labels words corresponding to the video；Each target labels word is matched in the theme dictionary pre-set, obtain target topic word corresponding to each target labels word difference, the theme dictionary pre-set includes descriptor and label word corresponding with the descriptor, the descriptor include with the meaning of a word of the label word similar in network hot word；By at least one target topic word, it is defined as subject name corresponding to the video.The playback volume of video can be improved using the embodiment of the present invention.
Description
Technical field
The present invention relates to video display arts field, more particularly to a kind of method and dress for generating video subject title
Put.
Background technology
Video playback amount is extremely important to video website, and the high video of playback volume can not only lift the well-known of video website
Degree, and the advertising income of video website can be improved.Because user is before video is played, generally mainly according to subject name
To judge whether video content is worth viewing, therefore, attractive subject name is the key for improving video playback amount.
At present, each video website generally determines subject name by the way of combination tag.Specifically, according to video
Content is that video adds multiple labels, combines multiple labels as subject name；Wherein, different labels may belong to different
Tag types, tag types can be age, region, style, channel, personage, video quality etc., and a subject name can wrap
Include multiple different types of labels.For example the subject name determined using combination tag mode can be star's A film collection
《XXX》, star's B portfolios.
However, with the fast development of internet, people can face a large amount of novel abundant network informations daily, above-mentioned
The subject name novelty determined by the way of combination tag is poor, has been difficult to the notice for attracting people.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of method and apparatus for generating video subject title, to realize increase
The playback volume of video.Concrete technical scheme is as follows：
In the one side that the present invention is implemented, there is provided a kind of method for generating video subject title, methods described include：
Obtain pre-set text information corresponding to video；
Cutting word processing is carried out to the pre-set text information, and using cutting word result as multiple corresponding to the video
Target labels word；
Each target labels word is matched in the theme dictionary pre-set, obtains each target labels word difference
Corresponding target topic word, the theme dictionary pre-set include descriptor and label corresponding with the descriptor
Word, the descriptor include with the meaning of a word of the label word similar in network hot word；
By at least one target topic word, it is defined as subject name corresponding to the video.
Optionally, the theme dictionary is pre-set as follows：
Descriptor is obtained, determines the meaning of a word of the descriptor；
Obtain label word similar in the meaning of a word with the descriptor；
By the descriptor and with the meaning of a word of the descriptor similar in label word, form the theme dictionary.
Optionally, the descriptor includes network hot word；
It is described to be matched each target labels word in the theme dictionary pre-set, obtain each target labels word
Corresponding to respectively the step of target topic word, including：
Each target labels word is matched in the theme dictionary pre-set, obtains each target labels word difference
Corresponding objective network hot word；
It is described by least one target topic word, the step of being defined as subject name corresponding to the video, including：
By at least one objective network hot word, it is defined as subject name corresponding to the video.
Optionally, at least one target topic word is defined as subject name corresponding to the video described
After step, methods described also includes：
By the history played data of targeted customer, it is defined as the input value of default click volume prediction model；
Using the default click volume prediction model, the preference theme that the targeted customer plays video is calculated；
When the subject name belongs to the preference theme, by the subject name and the video recommendations to described
Targeted customer.
Optionally, at least one target topic word is defined as subject name corresponding to the video described
After step, methods described also includes：
Subject name corresponding to the video is shown in the default page；
The default page is inserted into default information flow Feed advertisements, the Feed advertisements are located at and the subject name
Adjacent predeterminated position.
At the another aspect that the present invention is implemented, a kind of device for generating video subject title, described device bag are additionally provided
Include：
First acquisition unit, for obtaining pre-set text information corresponding to video；
Generation unit, for carrying out cutting word processing to the pre-set text information, and using cutting word result as described in
Multiple target labels words corresponding to video；
Matching unit, for each target labels word to be matched in the theme dictionary pre-set, obtain described each
Target labels word respectively corresponding to target topic word, the theme dictionary pre-set include descriptor and with the theme
Label word corresponding to word, the descriptor include with the meaning of a word of the label word similar in network hot word；
First determining unit, for by least one target topic word, being defined as subject corresponding to the video
Claim.
Optionally, the theme dictionary is by performing as lower unit is pre-set：
Second acquisition unit, for obtaining descriptor, determine the meaning of a word of the descriptor；
3rd acquiring unit, for obtaining label word similar in the meaning of a word with the descriptor；
Component units, for by the descriptor and with the meaning of a word of the descriptor similar in label word, described in composition
Theme dictionary.
Optionally, the descriptor includes network hot word；
First matching unit, specifically for carrying out each target labels word in the theme dictionary pre-set
Match somebody with somebody, obtain objective network hot word corresponding to each target labels word difference；
First determining unit, specifically for by least one objective network hot word, being defined as the video pair
The subject name answered.
Optionally, described device also includes：
Second determining unit, for by the history played data of targeted customer, being defined as default click volume prediction model
Input value；
Computing unit, for utilizing the default click volume prediction model, calculate the targeted customer and play video
Have a preference for theme；
Recommendation unit, for when the subject name belongs to the preference theme, by the subject name and described
Video recommendations give the targeted customer.
Optionally, described device also includes：
Display unit, for showing subject name corresponding to the video in the default page；
Unit is inserted, for default information flow Feed advertisements to be inserted into the default page, the Feed advertisements are located at
The predeterminated position adjacent with the subject name.
At the another aspect that the present invention is implemented, a kind of computer-readable recording medium is additionally provided, it is described computer-readable
Instruction is stored with storage medium, when run on a computer so that it is raw that computer performs any of the above-described described one kind
Into the method for video subject title.
At the another aspect that the present invention is implemented, the embodiment of the present invention additionally provides a kind of computer program production comprising instruction
Product, when run on a computer so that computer performs a kind of side of any of the above-described described generation video subject title
Method.
A kind of method and apparatus for generating video subject title provided in an embodiment of the present invention, first, obtain target video
Corresponding pre-set text information；Cutting word processing is carried out to pre-set text information, and using cutting word result as corresponding to video
Multiple target labels words；Then, each target labels word is matched in theme dictionary, it is right respectively obtains each target labels word
The target topic word answered, the theme dictionary pre-set include descriptor and label word corresponding with descriptor, descriptor bag
Include with the meaning of a word of label word similar in network hot word；Finally, by least one target topic word, it is defined as theme corresponding to video
Title.
Due to descriptor include with the meaning of a word of label word similar in network hot word, compared to traditional subject name, the present invention
The video subject title of embodiment generation is more attractive to user, so as to increase playback volume of the user to video.Certainly, implement
Any product or method of the present invention must be not necessarily required to reach all the above advantage simultaneously.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described.
Fig. 1 is a kind of flow chart of the method for the generation video subject title of the embodiment of the present invention；
Fig. 2 is another flow chart of the method for the generation video subject title of the embodiment of the present invention；
Fig. 3 a are the particular flow sheet that theme dictionary is pre-set in the embodiment of the present invention；
Fig. 3 b are another flow chart of the method for the generation video subject title of the embodiment of the present invention；
Fig. 4 is the structure chart of the device of the generation video subject title of the embodiment of the present invention；
Fig. 5 is the structure chart of the electronic equipment of the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is described.
Because video playback amount is extremely important to video website, the high video of playback volume can not only lift video website
Popularity, and the advertising income of video website can be improved.Because user is before video is played, generally mainly according to theme
Title is watched to judge whether video content is worth, and therefore, attractive subject name is the pass for improving video playback amount
Key.
At present, each video website generally determines subject name by the way of combination tag.Specifically, according to video
Content is that video adds multiple labels, combines multiple labels as subject name；Wherein, different labels may belong to different
Tag types, tag types can be age, region, style, channel, personage, video quality etc., and a subject name can wrap
Include multiple different types of labels.For example the subject name determined using combination tag mode can be star's A film collection
《XXX》, star's B portfolios.
But with the fast development of internet, people can face a large amount of novel abundant network informations daily, above-mentioned
The subject name novelty determined by the way of combination tag is poor, has been difficult to the notice for attracting people.
Based on this, it is contemplated that improve the playback volume of video by increasing the attraction of subject name, video can be lifted
The popularity of network and the advertising income of video website.
Based on above-mentioned consideration, in order to solve the problems, such as that the attraction of subject name present in prior art is poor, this hair
It is bright to provide a kind of method for generating video subject title, first, obtain pre-set text information corresponding to target video；To default
Text message carries out cutting word processing, and using cutting word result as multiple target labels words corresponding to video；Then, by each mesh
Mark label word is matched in theme dictionary, obtain each target labels word respectively corresponding to target topic word, pre-set
Theme dictionary includes descriptor and label word corresponding with descriptor, descriptor include with the meaning of a word of label word similar in network
Hot word；Finally, by least one target topic word, it is defined as subject name corresponding to video.Because descriptor includes and label
Network hot word similar in the meaning of a word of word, compared to traditional subject name, the video subject title of generation of the embodiment of the present invention to
Family is more attractive, so as to increase playback volume of the user to video.
The embodiment of the invention discloses a kind of method for generating video subject title, implements referring to Fig. 1, Fig. 1 for the present invention
A kind of flow chart of the method for the generation video subject title of example, comprises the following steps：
Step 101, pre-set text information corresponding to video is obtained.
In this step, pre-set text information corresponding to video is obtained, it is corresponding to obtain video according to pre-set text information
Multiple target labels words；Wherein, pre-set text information is set in advance corresponding to video.
In actual applications, pre-set text information includes title, label and description of video etc., such as, regarded for one
It is frequently, entitled that " star A Chinese vindication star B ", label are " star A " and " star B ", video are described as that " star A's is red
Hear " etc..
Step 102, cutting word processing is carried out to the pre-set text information, and using cutting word result as the video pair
The multiple target labels words answered.
In this step, first, cutting word processing is carried out to the pre-set text information of video, then, by cutting word result
As multiple target labels words corresponding to video, with target topic word corresponding to being obtained according to target labels word.
In actual applications, default cutting word model can be used to carry out cutting word processing, due to using switch mode to text
This information carries out cutting word processing and belongs to prior art, will not be repeated here.
Such as to the title of video " star A carries out cutting word processing with Chinese vindication star B ", obtain " star A ", " use ",
" Chinese ", " vindication ", " this 5 target labels words of star B ".
Step 103, each target labels word is matched in the theme dictionary pre-set, obtains each target mark
Sign target topic word corresponding to word difference.
Wherein, the theme dictionary pre-set includes descriptor and label word corresponding with the descriptor, institute
State descriptor include with the meaning of a word of the label word similar in network hot word.
In this step, in the theme dictionary pre-set, each target labels word is matched, obtains each target mark
Sign target topic word corresponding to word；Due to target topic word include with the meaning of a word of target labels word similar in network hot word, therefore,
Compared to target labels word, target topic word has feeling of freshness, to user's more attractive.
Such as when the theme dictionary pre-set includes descriptor " Europe bar " and mark corresponding with descriptor " Europe bar "
Signing word, " during star A ", " star A " matching result is just target topic word " Europe bar " to target labels word.
In actual applications, descriptor is in addition to including instantly popular network hot word, network short sentence, can also be through
Allusion quotation poem, Chinese idiom, red-letter day are done something for the occasion word etc., that is to say, that every user is interested, has the word of clear and definite implication or sentence all
Descriptor can be used as.
For example descriptor can be network hot word " city can play ", " Bai Fumei ", " monkey plug thunder "；" picture is too beautiful for network short sentence
I dare not see "；Chinese idiom " overbearing and insufferably arrogant "；" red bean gives birth to the southern part of the country, and the spring is sent out several for classical verse；It is willing to that monarch picks more, this thing most phase
Think "；Red-letter day does something for the occasion word " mother is beauty, and the years please not injure her " etc..
It should be noted that in the theme dictionary pre-set, descriptor and label word corresponding with descriptor are not
Must be one-to-one relation, that is to say, that a descriptor can correspond to multiple label words, and a label word can correspond to
Multiple descriptor.
For example in the theme dictionary pre-set, label word corresponding to descriptor " Europe bar " includes " star A ", " star
C ", " name of multiple South Korea's matinée idols such as star D "；" descriptor corresponding to star A " includes " Europe bar " to label word, " its people are old
It is public " etc..
Step 104, by least one target topic word, it is defined as subject name corresponding to the video.
In this step, multiple target labels words are matched at least one target master in obtained multiple target topic words
Epigraph, as subject name corresponding to video.
In actual applications, it can be chosen from multiple target topic words corresponding to video and at least one be used as subject
Claim, this can also be any limitation as in the embodiment of the present invention using target topic contamination as subject name.In addition, one
Individual video can correspond to multiple subject names.
For example the target labels word of video is " star A " and " star B ", the target labels word " mesh that star A " matchings obtain
Mark descriptor is " Europe bar " and " national husband ", and " the target topic word that star B " matchings obtain is " national first to target labels word
Love ", can be from three target topic words " Europe bar ", " national husband " and at least one conduct video of " national first love " middle selection
Corresponding subject name.
Subject name corresponding to the video so obtained includes the network hot word to attract eyeball, has feeling of freshness, to user
More attractive.
It can be seen that in embodiments of the present invention, can be according to the target labels word of video, in the theme dictionary pre-set
Matched, obtain target topic word corresponding to each target labels word difference, wherein, epigraph storehouse includes descriptor and and theme
Label word corresponding to word, descriptor include with the meaning of a word of label word similar in network hot word, then by least one target topic word
It is defined as subject name corresponding to video.Due to descriptor include with the meaning of a word of label word similar in network hot word, compared to tradition
Subject name, the video subject title of generation is more attractive to user, so as to increase playback volume of the user to video；This
Outside, allow user to feel that the subject name of " the warm heart " can make a profound impression to user, the well-known of company is improved by public praise effect
Degree.
When descriptor includes network hot word, the embodiment of the present invention discloses a kind of side for generating video subject title again
Method, referring to Fig. 2, Fig. 2 is another flow chart of the method for the generation video subject title of the embodiment of the present invention, including walks as follows
Suddenly：
Step 201, pre-set text information corresponding to video is obtained.
The detailed process and technique effect of this step may be referred in the method for the generation video subject title shown in Fig. 1
Step 101, will not be repeated here.
Step 202, cutting word processing is carried out to the pre-set text information, and using cutting word result as the video pair
The multiple target labels words answered.
The detailed process and technique effect of this step may be referred in the method for the generation video subject title shown in Fig. 1
Step 102, will not be repeated here.
Step 203, each target labels word is matched in the theme dictionary pre-set, obtains each target mark
Sign objective network hot word corresponding to word difference.
Wherein, the theme dictionary pre-set includes network hot word and label word corresponding with network hot word.
In this step, in the theme dictionary pre-set, each target labels word is matched, obtains each target mark
Objective network hot word corresponding to word is signed, compared to target labels word, target topic word has feeling of freshness, to user's more attractive.
For example the theme dictionary pre-set includes network hot word " monkey matches thunder " and label corresponding with " monkey matches thunder "
Word " ox people ", network hot word " power of chaotic state " and outgoing label word " doing the best " corresponding with " power of chaotic state ", and the target of video
Label word includes " ox people " and " doing the best ", then, the matching result of target labels word " ox people " just for objective network hot word, " match by monkey
Thunder ", the matching result of target labels word " doing the best " is just objective network hot word " power of chaotic state ".
So, can be obtained by label word according to the pre-set text information expansion of video more come matching network hot word
Network hot word so that subject name corresponding to the video finally given is more attractive.
Step 204, by least one objective network hot word, it is defined as subject name corresponding to the video.
In this step, multiple target labels words are matched at least one target in obtained multiple objective network hot words
Network hot word, as subject name corresponding to video.
For example the target labels word of video is " ox people " and " doing the best ", target labels word " ox people " matches obtained target
Network hot word is " monkey matches thunder ", and the objective network hot word that target labels word " doing the best " matching obtains is " power of chaotic state ", then, can
The video is used as to choose at least one objective network hot word from two objective network hot words " monkey matches thunder " and " power of chaotic state "
Corresponding subject name.
Subject name corresponding to the video so obtained is made up of the network boom word to attract eyeball, has feeling of freshness, to
Family more attractive.
It can be seen that in embodiments of the present invention, can be according to the target labels word of video, in the theme dictionary pre-set
Matched, obtain each target labels word respectively corresponding to objective network hot word, wherein, epigraph storehouse include network hot word and with
Label word corresponding to network hot word, then at least one network hot word is defined as subject name corresponding to video.Due to network boom
Word is instantly the most popular word, and compared to traditional subject name, the subject name being made up of network boom word has more to user
Attraction, so as to increase playback volume of the user to video.
In a kind of alternative embodiment of the present invention, referring to Fig. 3 a, Fig. 3 a are to pre-set theme in the embodiment of the present invention
The particular flow sheet of dictionary, comprises the following steps：
Step 301, descriptor is obtained, determines the meaning of a word of the descriptor.
In this step, first, descriptor is obtained；In actual applications, descriptor can be instantly popular network boom
Word, network short sentence or classical poem, Chinese idiom, red-letter day are done something for the occasion word etc., that is to say, that every user is interested, has
The word or sentence for specifying implication can be used as descriptor.
For example descriptor can be network hot word " city can play ", " Bai Fumei ", " monkey plug thunder "；" picture is too beautiful for network short sentence
I dare not see "；Chinese idiom " overbearing and insufferably arrogant "；" red bean gives birth to the southern part of the country, and the spring is sent out several for classical verse；It is willing to that monarch picks more, this thing most phase
Think "；Red-letter day does something for the occasion word " mother is beauty, and the years please not injure her " etc..
Then, it is determined that the implication of descriptor.In order to get with the meaning of a word of descriptor similar in label word, it is necessary to elder generation
Determine the implication of descriptor.But the meaning of a word of some descriptor be not easy it is short from literal understanding, especially network hot word and network
Sentence.
For example the meaning of a word of descriptor " picture too beautiful I dare not see " can be construed to hunt for novelty or can't bear to look at straight；Descriptor
The meaning of a word of " monkey plug thunder " can be construed to intelligent, ox people, rising star；The meaning of a word of descriptor " overbearing and insufferably arrogant " can be construed to it is wildly arrogant,
It is arrogant；" red bean gives birth to the southern part of the country to descriptor, and the spring is sent out several；Be willing to monarch more pick, this thing most yearning between lovers " the meaning of a word can be construed to yearning between lovers,
Miss, bitter love；The meaning of a word of descriptor " mother is a beauty, and the years please not injure her " can be construed to the Mother's Day, Ma Majie.
Step 302, label word similar in the meaning of a word with the descriptor is obtained.
In this step, label word similar in the meaning of a word with descriptor is obtained.It should be understood that come for a descriptor
Say, with the meaning of a word of descriptor similar in label word may have it is multiple.
Such as with the meaning of a word of descriptor " picture too beautiful I dare not see " similar in label word can include " hunting for novelty " and " no
Bear direct-view "；With the meaning of a word of descriptor " monkey plug thunder " similar in label word can include " intelligent ", " ox people " and " rising star "；With master
Label word similar in writing inscription the meaning of a word of " overbearing and insufferably arrogant " can include " wildly arrogant " and " arrogant "；" red bean gives birth to the southern part of the country, spring with descriptor
To send out several；Be willing to monarch more pick, this thing most yearning between lovers " the meaning of a word similar in label word can include " yearning between lovers ", " miss " and " hardship
Love "；With the meaning of a word of descriptor " mother is beauty, and the years please not injure her " similar in label word can include " Mother's Day "
" mother's section ".
Step 303, by the descriptor and with the meaning of a word of the descriptor similar in label word, form the descriptor
Storehouse.
In this step, by descriptor and with the meaning of a word of descriptor similar in label word, form theme dictionary.Namely
Say, theme dictionary include descriptor, with the meaning of a word of descriptor similar in label word and descriptor it is close with the meaning of a word of descriptor
Label word between corresponding relation；In theme dictionary, according to similar in a descriptor can find at least one meaning of a word
Label word, certainly, the descriptor according to similar in a label word can also find at least one meaning of a word.
In this manner it is possible to theme dictionary is based on, according to the label word of the pre-set text information cutting word generation by video, matching
To descriptor similar in the individual and meaning of a word of label word, and then according to the subject name of descriptor generation video, the subject of video
Claim the implication that can not only embody original preset text message, and it is more attractive to user.
For example in theme dictionary, according to label word " hunting for novelty " and " can't bear to look at straight ", descriptor " picture can be matched
Too it is beautiful I dare not see "；According to label word " intelligent ", " ox people " and " rising star ", descriptor " monkey plug thunder " can be matched；According to mark
Word " yearning between lovers ", " miss " and " bitter love " is signed, can matching descriptor, " the red bean life southern part of the country, spring are sent out several；It is willing to that monarch picks more,
This thing most yearning between lovers "；According to label word " Mother's Day " and " mother's section ", can matching descriptor, " mother is a beauty, and the years please
Her is not injured ".
In addition, in order that descriptor can keep feeling of freshness and attraction in theme dictionary, can be at any time to theme dictionary
Middle descriptor and with the meaning of a word of descriptor similar in label word increased, changed and deleted, increase new descriptor, modification
Wrong descriptor and with the meaning of a word of descriptor similar in label word, delete out-of-date descriptor and the meaning of a word with descriptor
Similar label word.
In actual applications, the step 102 in the generation video subject title of the embodiment of the present invention shown in Fig. 1 is performed
Afterwards, can also according to corresponding to the integrated mode storehouse generation video pre-set subject name, specific step is as follows：
The first step, obtain and preset tag types corresponding to each target labels word difference.
In this step, tag types are preset corresponding to each target labels word difference acquired；In actual applications,
Default tag types include " age ", " region ", " style ", " channel ", " personage ", " video quality ", " type " etc..
For example video A target labels word is including " animation A " and " warm blood ", " tag types are preset corresponding to animation A " is
" channel ", it is " type " that tag types are preset corresponding to " warm blood ".
Second step, according to default tag types, matched in the integrated mode storehouse pre-set, video pair must be determined
The theme integrated mode answered.
Wherein, the integrated mode storehouse pre-set includes the integrated mode being made up of at least two tag types, usual feelings
Under condition, integrated mode storehouse can include tens kinds of integrated modes.
In this step, tag types are preset according to corresponding to each target labels word difference, in the combination die pre-set
Formula is matched in storehouse, determines theme integrated mode corresponding to video.
For example integrated mode storehouse includes the theme built-up pattern of " type "+" channel ", and the target mark that video A includes
Label word " preset that tag types are " channels ", tag types are preset corresponding to " warm blood " is " type " corresponding to animation A ", then,
Video A can match " type "+" channel " the theme built-up pattern in integrated mode storehouse.
3rd step, target topic word is reconfigured according to fixed theme integrated mode, generation video is corresponding
Subject name.
In this step, according to fixed theme built-up pattern, target topic word is reconfigured, generates video
Corresponding subject name.
For example the theme built-up patterns that are matched in integrated mode storehouse of video A are " type "+" channel ", and video A bags
" it is " channel " that tag types are preset corresponding to animation A " to the target labels word included, is marked with advance corresponding to target labels word " warm blood "
It is " type " to sign type, then, can according to " type "+" channel " theme built-up pattern, by target labels word " animation A " and
" warm blood " is reconfigured, and subject name corresponding to generation video is " warm blood animation A ".
It should be noted that for same video, multiple theme built-up patterns may be matched, and then obtain multiple
Subject name.
So, each target labels word of video can be entered according to the theme built-up pattern in default integrated mode storehouse
Row reconfigures, and obtains the subject name of the video of novelty, to attract the notice of user, improves the playback volume of video.
In a kind of alternative embodiment of the present invention again, in a kind of generation video master of the embodiment of the present invention shown in Fig. 1
Inscribe one's name in the method claimed after step 104, the preference theme of video can also be played according to user, by the subject name of video with
And video recommendations are to user.With reference to figure 3b, Fig. 3 b are the another kind of the method for the generation video subject title of the embodiment of the present invention
Flow chart, method also include：
Step 11, pre-set text information corresponding to video is obtained.
The detailed process and technique effect of this step may be referred in the method for the generation video subject title shown in Fig. 1
Step 101, will not be repeated here.
Step 12, cutting word processing is carried out to the pre-set text information, and using cutting word result as the video pair
The multiple target labels words answered.
The detailed process and technique effect of this step may be referred in the method for the generation video subject title shown in Fig. 1
Step 102, will not be repeated here.
Step 13, each target labels word is matched in the theme dictionary pre-set, obtains each target mark
Target topic word corresponding to word difference is signed, the theme dictionary pre-set includes descriptor and should with the topic word pair
Label word, the descriptor include with the meaning of a word of the label word similar in network hot word.
The detailed process and technique effect of this step may be referred in the method for the generation video subject title shown in Fig. 1
Step 103, will not be repeated here.
Step 14, by least one target topic word, it is defined as subject name corresponding to the video.
The detailed process and technique effect of this step may be referred in the method for the generation video subject title shown in Fig. 1
Step 104, will not be repeated here.
Step 15, when the subject name, which belongs to targeted customer, plays the preference theme of video, by the subject name
And the video recommendations give the targeted customer.
In this step, the preference theme of targeted customer's broadcasting video is being calculated using default click volume prediction model
Afterwards, if the subject name of video belongs to the preference theme that user plays video, subject name and video recommendations are given should
Targeted customer, to improve the playback volume of video.
In actual applications, the inclined of video is played, it is necessary to perform following steps to calculate targeted customer before step 15
Like theme：
The first step, by the history played data of targeted customer, it is defined as the input value of default click volume prediction model.
In this step, the history played data of targeted customer is defined as to the input value of default click volume prediction model,
Default click volume prediction model is enabled to calculate the preference theme that targeted customer plays video.
Wherein, the history played data according to user can be calculated user and broadcast by default click volume prediction model
The preference theme of video is put, wherein, default click volume prediction model can be according to reference to prior art, the embodiment of the present invention pair
This is repeated no more.
Second step, using the default click volume prediction model, calculate the preference master that the targeted customer plays video
Topic.
In this step, the preference theme of targeted customer's broadcasting video is calculated using default click volume prediction model so that
The preference theme of video can be played according to targeted customer, recommends possible subject name and video interested for targeted customer,
Improve the playback volume of video.
So, the method for the subject name for generating video is recommended to associate with user, can be played and regarded according to user
The hobby of frequency, by the subject name of video and video recommendations to user, the usage experience of user is improved, increases the broadcasting of video
Amount；Further, since the subject name of video is network hot word similar in the meaning of a word gone out by the pre-set text information expansion of video,
Subject name is recommended into targeted customer so that recommendation results more dissipate.
In another a kind of alternative embodiment of the invention, in a kind of generation video master of the embodiment of the present invention shown in Fig. 1
Inscribe one's name in the method claimed after step 104, method also includes：
Subject name corresponding to the video is shown in the default page；
The default page is inserted into default information flow Feed advertisements, the Feed advertisements are located at and the subject name
Adjacent predeterminated position.
In actual applications, Feed advertisements can accurately be matched according to user characteristics, be that every user customizes individual character
The advertisement of change, harassing of advertisement degree is preferably minimized.Compared to conventional ads, not only the reception degree of user is higher, and advertisement is sought
The purpose crowd of pin is also more accurate.And in video website, due to user, residence time is shorter in homepage recommends the page,
And will not generally return again to homepage and recommend the page, therefore, homepage recommends to be not suitable for insertion Feed advertisements in the page.Simultaneously as
The video similarity shown in the associated recommendation of the broadcasting page is higher, and injury of the insertion Feed advertisements to Consumer's Experience is larger, can
See, play and be also not suitable for inserting Feed advertisements in the associated recommendation of the page.
Therefore, in embodiments of the present invention, default Feed advertisements can be inserted into the subject name of display video
On the default page.Specifically, Feed advertisements can be located at the predeterminated position adjacent with subject name, such as, can be in every 5 masters
Autograph inserts a Feed advertisement between being referred to as.So, because the subject name of video is more attractive, user can be grasped by pulling down
More video subject titles are checked, so, the Feed advertisements being interspersed between the subject name of video can just show
User, can not only meet the viewing demand of user, and add the advertising income of video website.
The embodiment of the present invention separately discloses a kind of method for generating video subject title, real for the present invention referring to Fig. 4, Fig. 4
The structure chart of the device of the generation video subject title of example is applied, the device includes：
First acquisition unit 401, for obtaining pre-set text information corresponding to video；
Generation unit 402, for carrying out cutting word processing to the pre-set text information, and using cutting word result as institute
State multiple target labels words corresponding to video；
Matching unit 403, for each target labels word to be matched in the theme dictionary pre-set, obtain described
Each target labels word respectively corresponding to target topic word, the theme dictionary pre-set include descriptor and with the master
Label word corresponding to epigraph, the descriptor include with the meaning of a word of the label word similar in network hot word；
First determining unit 404, for by least one target topic word, being defined as theme corresponding to the video
Title.
In a kind of alternative embodiment of the present invention, the theme dictionary is by performing as lower unit is pre-set：
Second acquisition unit, for obtaining descriptor, determine the meaning of a word of the descriptor；
3rd acquiring unit, for obtaining label word similar in the meaning of a word with the descriptor；
Component units, for by the descriptor and with the meaning of a word of the descriptor similar in label word, described in composition
Theme dictionary.
In another alternative embodiment of the present invention, the descriptor includes network hot word；
Matching unit 403, specifically for each target labels word is matched in the theme dictionary pre-set, obtain
Objective network hot word corresponding to each target labels word difference；
First determining unit 404, it is corresponding specifically for by least one objective network hot word, being defined as the video
Subject name.
In another alternative embodiment of the present invention, described device also includes：
Second determining unit, for by the history played data of targeted customer, being defined as default click volume prediction model
Input value；
Computing unit, for utilizing the default click volume prediction model, calculate the targeted customer and play video
Have a preference for theme；
Recommendation unit, for when the subject name belongs to the preference theme, by the subject name and described
Video recommendations give the targeted customer.
In another alternative embodiment of the present invention, described device also includes：
Display unit, for showing subject name corresponding to the video in the default page；
Unit is inserted, for default information flow Feed advertisements to be inserted into the default page, the Feed advertisements are located at
The predeterminated position adjacent with the subject name.
It can be seen that in embodiments of the present invention, can be according to the target labels word of video, in the theme dictionary pre-set
Matched, obtain target topic word corresponding to each target labels word difference, wherein, epigraph storehouse includes descriptor and and theme
Label word corresponding to word, descriptor include with the meaning of a word of label word similar in network hot word, then by least one target topic word
It is defined as subject name corresponding to video.Due to descriptor include with the meaning of a word of label word similar in network hot word, compared to tradition
Subject name, the video subject title of generation is more attractive to user, so as to increase playback volume of the user to video.
The embodiment of the present invention discloses a kind of electronic equipment again, as shown in figure 5, including processor 501, communication interface 502,
Memory 503 and communication bus 504, wherein, processor 501, communication interface 502, memory 503 is complete by communication bus 504
Into mutual communication,
Memory 503, for depositing computer program；
Processor 501, during for performing the program deposited on memory 503, performing in the above embodiment of the present invention and appointing
The one generation video subject title method.
The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, abbreviation PCI) bus or EISA (Extended Industry Standard
Architecture, abbreviation EISA) bus etc..The communication bus can be divided into address bus, data/address bus, controlling bus etc..
For ease of representing, only represented in figure with a thick line, it is not intended that an only bus or a type of bus.
The communication that communication interface is used between above-mentioned electronic equipment and other equipment.
Memory can include random access memory (Random Access Memory, abbreviation RAM), can also include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be at least one storage device for being located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
Abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor
(Digital Signal Processing, abbreviation DSP), application specific integrated circuit (Application Specific
Integrated Circuit, abbreviation ASIC), field programmable gate array (Field-Programmable Gate Array,
Abbreviation FPGA) either other PLDs, discrete gate or transistor logic, discrete hardware components.
In another embodiment provided by the invention, a kind of computer-readable recording medium is additionally provided, the computer can
Read to be stored with instruction in storage medium, when run on a computer so that computer performs any institute in above-described embodiment
A kind of method for the generation video subject title stated.
In another embodiment provided by the invention, a kind of computer program product for including instruction is additionally provided, when it
When running on computers so that computer performs a kind of side of any described generation video subject title in above-described embodiment
Method.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or its any combination real
It is existing.When implemented in software, can realize in the form of a computer program product whole or in part.The computer program
Product includes one or more computer instructions.When loading on computers and performing the computer program instructions, all or
Partly produce according to the flow or function described in the embodiment of the present invention.The computer can be all-purpose computer, special meter
Calculation machine, computer network or other programmable devices.The computer instruction can be stored in computer-readable recording medium
In, or the transmission from a computer-readable recording medium to another computer-readable recording medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, numeral from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer-readable recording medium can be any usable medium that computer can access or
It is the data storage devices such as server, the data center integrated comprising one or more usable mediums.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disc
Solid State Disk (SSD)) etc..
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Other identical element also be present in process, method, article or equipment including the key element.
Each embodiment in this specification is described by the way of related, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for system
For applying example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
Claims (11)
- A kind of 1. method for generating video subject title, it is characterised in that methods described includes：Obtain pre-set text information corresponding to video；Cutting word processing is carried out to the pre-set text information, and using cutting word result as multiple targets corresponding to the video Label word；Each target labels word is matched in the theme dictionary pre-set, each target labels word is obtained and corresponds to respectively Target topic word, the theme dictionary pre-set includes descriptor and label word corresponding with the descriptor, institute State descriptor include with the meaning of a word of the label word similar in network hot word；By at least one target topic word, it is defined as subject name corresponding to the video.
- 2. according to the method for claim 1, it is characterised in that the theme dictionary is pre-set as follows：Descriptor is obtained, determines the meaning of a word of the descriptor；Obtain label word similar in the meaning of a word with the descriptor；By the descriptor and with the meaning of a word of the descriptor similar in label word, form the theme dictionary.
- 3. according to the method for claim 1, it is characterised in that the descriptor includes network hot word；It is described to be matched each target labels word in the theme dictionary pre-set, obtain each target labels word difference The step of corresponding target topic word, including：Each target labels word is matched in the theme dictionary pre-set, each target labels word is obtained and corresponds to respectively Objective network hot word；It is described by least one target topic word, the step of being defined as subject name corresponding to the video, including：By at least one objective network hot word, it is defined as subject name corresponding to the video.
- 4. according to the method for claim 1, it is characterised in that described by least one target topic word, it is determined that After corresponding to the video the step of subject name, methods described also includes：By the history played data of targeted customer, it is defined as the input value of default click volume prediction model；Using the default click volume prediction model, the preference theme that the targeted customer plays video is calculated；When the subject name belongs to the preference theme, the subject name and the video recommendations are given to the target User.
- 5. according to the method for claim 1, it is characterised in that described by least one target topic word, it is determined that After corresponding to the video the step of subject name, methods described also includes：Subject name corresponding to the video is shown in the default page；The default page is inserted into default information flow Feed advertisements, the Feed advertisements are positioned at adjacent with the subject name Predeterminated position.
- 6. a kind of device for generating video subject title, it is characterised in that described device includes：First acquisition unit, for obtaining pre-set text information corresponding to video；Generation unit, for carrying out cutting word processing to the pre-set text information, and using cutting word result as the video Corresponding multiple target labels words；Matching unit, for each target labels word to be matched in the theme dictionary pre-set, obtain each target Label word respectively corresponding to target topic word, the theme dictionary pre-set include descriptor and with the topic word pair The label word answered, the descriptor include with the meaning of a word of the label word similar in network hot word；First determining unit, for by least one target topic word, being defined as subject name corresponding to the video.
- 7. device according to claim 6, it is characterised in that the theme dictionary is by performing as lower unit is set in advance Put：Second acquisition unit, for obtaining descriptor, determine the meaning of a word of the descriptor；3rd acquiring unit, for obtaining label word similar in the meaning of a word with the descriptor；Component units, for by the descriptor and with the meaning of a word of the descriptor similar in label word, form the theme Dictionary.
- 8. device according to claim 6, it is characterised in that the descriptor includes network hot word；First matching unit, specifically for each target labels word is matched in the theme dictionary pre-set, obtain To objective network hot word corresponding to each target labels word difference；First determining unit, specifically for being defined as at least one objective network hot word corresponding to the video Subject name.
- 9. device according to claim 6, it is characterised in that described device also includes：Second determining unit, for by the history played data of targeted customer, being defined as the defeated of default click volume prediction model Enter value；Computing unit, for utilizing the default click volume prediction model, calculate the preference that the targeted customer plays video Theme；Recommendation unit, for when the subject name belong to it is described preference theme when, by the subject name and the video Recommend the targeted customer.
- 10. device according to claim 6, it is characterised in that described device also includes：Display unit, for showing subject name corresponding to the video in the default page；Unit is inserted, for default information flow Feed advertisements to be inserted into the default page, the Feed advertisements are located at and institute State the adjacent predeterminated position of subject name.
- 11. a kind of electronic equipment, it is characterised in that including processor, communication interface, memory and communication bus, wherein, processing Device, communication interface, memory complete mutual communication by communication bus；Memory, for depositing computer program；Processor, during for performing the program deposited on memory, realize any described method and steps of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710594407.5A CN107463552A (en) | 2017-07-20 | 2017-07-20 | A kind of method and apparatus for generating video subject title |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710594407.5A CN107463552A (en) | 2017-07-20 | 2017-07-20 | A kind of method and apparatus for generating video subject title |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107463552A true CN107463552A (en) | 2017-12-12 |
Family
ID=60546168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710594407.5A Pending CN107463552A (en) | 2017-07-20 | 2017-07-20 | A kind of method and apparatus for generating video subject title |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107463552A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107977363A (en) * | 2017-12-20 | 2018-05-01 | 北京百度网讯科技有限公司 | Title generation method, device and electronic equipment |
| CN108460131A (en) * | 2018-03-02 | 2018-08-28 | 北京奇艺世纪科技有限公司 | A kind of tag along sort processing method and processing device |
| CN110019955A (en) * | 2017-12-15 | 2019-07-16 | 青岛聚看云科技有限公司 | A kind of video tab mask method and device |
| CN110309355A (en) * | 2018-06-15 | 2019-10-08 | 腾讯科技（深圳）有限公司 | Generation method, device, equipment and the storage medium of content tab |
| CN110555136A (en) * | 2018-03-29 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Video tag generation method and device and computer storage medium |
| CN113590804A (en) * | 2021-06-23 | 2021-11-02 | 北京百度网讯科技有限公司 | Video theme generation method and device and electronic equipment |
| CN114938477A (en) * | 2022-06-23 | 2022-08-23 | 阿里巴巴（中国）有限公司 | Video topic determination method, device and equipment |
| CN116156271A (en) * | 2022-12-14 | 2023-05-23 | 北京奇艺世纪科技有限公司 | Video title generation method and device, electronic equipment and readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708498A (en) * | 2012-01-13 | 2012-10-03 | 合一网络技术(北京)有限公司 | Theme orientation based advertising method |
| CN103942340A (en) * | 2014-05-09 | 2014-07-23 | 电子科技大学 | Microblog user interest recognizing method based on text mining |
| CN104391942A (en) * | 2014-11-25 | 2015-03-04 | 中国科学院自动化研究所 | Short text characteristic expanding method based on semantic atlas |
| CN104679848A (en) * | 2015-02-13 | 2015-06-03 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN104699844A (en) * | 2015-03-31 | 2015-06-10 | 北京奇艺世纪科技有限公司 | Method and device for determining video tags for advertisements |
| CN104853230A (en) * | 2015-05-14 | 2015-08-19 | 无锡天脉聚源传媒科技有限公司 | Hot-spot video push method and apparatus |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN105069102A (en) * | 2015-08-03 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN106126619A (en) * | 2016-06-20 | 2016-11-16 | 中山大学 | A kind of video retrieval method based on video content and system |
| CN106407168A (en) * | 2016-09-06 | 2017-02-15 | 首都师范大学 | Automatic generation method for practical writing |
| CN106503255A (en) * | 2016-11-15 | 2017-03-15 | 科大讯飞股份有限公司 | Based on the method and system that description text automatically generates article |
| CN106919575A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | application program searching method and device |
-
2017
- 2017-07-20 CN CN201710594407.5A patent/CN107463552A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708498A (en) * | 2012-01-13 | 2012-10-03 | 合一网络技术(北京)有限公司 | Theme orientation based advertising method |
| CN103942340A (en) * | 2014-05-09 | 2014-07-23 | 电子科技大学 | Microblog user interest recognizing method based on text mining |
| CN104391942A (en) * | 2014-11-25 | 2015-03-04 | 中国科学院自动化研究所 | Short text characteristic expanding method based on semantic atlas |
| CN104679848A (en) * | 2015-02-13 | 2015-06-03 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN104699844A (en) * | 2015-03-31 | 2015-06-10 | 北京奇艺世纪科技有限公司 | Method and device for determining video tags for advertisements |
| CN104853230A (en) * | 2015-05-14 | 2015-08-19 | 无锡天脉聚源传媒科技有限公司 | Hot-spot video push method and apparatus |
| CN104965890A (en) * | 2015-06-17 | 2015-10-07 | 深圳市腾讯计算机系统有限公司 | Advertisement recommendation method and apparatus |
| CN105069102A (en) * | 2015-08-03 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Information push method and apparatus |
| CN106919575A (en) * | 2015-12-24 | 2017-07-04 | 北京奇虎科技有限公司 | application program searching method and device |
| CN106126619A (en) * | 2016-06-20 | 2016-11-16 | 中山大学 | A kind of video retrieval method based on video content and system |
| CN106407168A (en) * | 2016-09-06 | 2017-02-15 | 首都师范大学 | Automatic generation method for practical writing |
| CN106503255A (en) * | 2016-11-15 | 2017-03-15 | 科大讯飞股份有限公司 | Based on the method and system that description text automatically generates article |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110019955A (en) * | 2017-12-15 | 2019-07-16 | 青岛聚看云科技有限公司 | A kind of video tab mask method and device |
| CN107977363A (en) * | 2017-12-20 | 2018-05-01 | 北京百度网讯科技有限公司 | Title generation method, device and electronic equipment |
| CN107977363B (en) * | 2017-12-20 | 2021-12-17 | 北京百度网讯科技有限公司 | Title generation method and device and electronic equipment |
| CN108460131A (en) * | 2018-03-02 | 2018-08-28 | 北京奇艺世纪科技有限公司 | A kind of tag along sort processing method and processing device |
| CN110555136A (en) * | 2018-03-29 | 2019-12-10 | 优酷网络技术（北京）有限公司 | Video tag generation method and device and computer storage medium |
| CN110555136B (en) * | 2018-03-29 | 2022-07-08 | 阿里巴巴（中国）有限公司 | Video tag generation method and device and computer storage medium |
| CN110309355A (en) * | 2018-06-15 | 2019-10-08 | 腾讯科技（深圳）有限公司 | Generation method, device, equipment and the storage medium of content tab |
| CN113590804A (en) * | 2021-06-23 | 2021-11-02 | 北京百度网讯科技有限公司 | Video theme generation method and device and electronic equipment |
| CN113590804B (en) * | 2021-06-23 | 2023-08-04 | 北京百度网讯科技有限公司 | Video theme generation method and device and electronic equipment |
| CN114938477A (en) * | 2022-06-23 | 2022-08-23 | 阿里巴巴（中国）有限公司 | Video topic determination method, device and equipment |
| CN114938477B (en) * | 2022-06-23 | 2024-05-03 | 阿里巴巴（中国）有限公司 | Video topic determination method, device and equipment |
| CN116156271A (en) * | 2022-12-14 | 2023-05-23 | 北京奇艺世纪科技有限公司 | Video title generation method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463552A (en) | A kind of method and apparatus for generating video subject title | |
| US12080046B2 (en) | Systems and methods for automatic image generation and arrangement using a machine learning architecture | |
| Bishop | Anxiety, panic and self-optimization: Inequalities and the YouTube algorithm | |
| US9405734B2 (en) | Image manipulation for web content | |
| WO2017045592A1 (en) | Advertisement display method and apparatus for controllable electronic screen | |
| JP2008538842A5 (en) | ||
| CN102084386A (en) | Keyword-advertisement method using meta-information related to digital contents and system thereof | |
| CN104182481B (en) | Resource recommendation method and device | |
| TW201108004A (en) | Server apparatus, electronic apparatus, electronic book providing system, electronic book providing method, electronic book displaying method, and program | |
| US11763546B1 (en) | Systems and methods for managing computer memory for scoring images or videos using selective web crawling | |
| CN109345303B (en) | Rich media advertisement putting method and device | |
| CN110059221B (en) | Video recommendation method, electronic device and computer readable storage medium | |
| US9449231B2 (en) | Computerized systems and methods for generating models for identifying thumbnail images to promote videos | |
| US20160381433A1 (en) | Information distribution device, information distribution method, and program | |
| CN104462339B (en) | The method for pushing and device of multimedia file | |
| CN107846615A (en) | Visualize advertisement delivery system, put-on method and advertisement broadcast method | |
| Song et al. | Predicting content similarity via multimodal modeling for video-in-video advertising | |
| KR102149035B1 (en) | Advertising page creation and management system for performance marketing | |
| Xu et al. | The medal war in peacetime: Examining nationalistic notions embedded in CCTV’s coverage of gymnastics in the 2016 Rio Summer Olympics | |
| CN103593382A (en) | Information processing apparatus, information processing method, and program | |
| CN117391776B (en) | Advertisement putting method and device, electronic equipment and storage medium | |
| CN116614652A (en) | Advertisement video clip replacement method, device and storage medium in live broadcast scene | |
| CN114996553A (en) | Dynamic video cover generation method | |
| CN206712985U (en) | A kind of new network video push system | |
| CN109784967A (en) | A kind of method for pushing and device of information |
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 |