CN103984699A - Pushing method and pushing device for promotion information - Google Patents
Pushing method and pushing device for promotion information Download PDFInfo
- Publication number
- CN103984699A CN103984699A CN201410148385.6A CN201410148385A CN103984699A CN 103984699 A CN103984699 A CN 103984699A CN 201410148385 A CN201410148385 A CN 201410148385A CN 103984699 A CN103984699 A CN 103984699A
- Authority
- CN
- China
- Prior art keywords
- file
- fragment
- promotion message
- multimedia file
- candidate
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/489—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using time information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention provides a pushing method and a pushing device for promotion information. In the embodiment of the invention, the time range corresponding to a head leader and/or tail leader of a multimedia file is obtained and then the target promotion information is pushed according to the time range during the playing of the head leader and/or tail leader of the multimedia file. Since the head leader and/or tail leader of the multimedia file is generally unique repetitive contents, viewers of the multimedia file do not pay attention to the contents at the part, the target promotion information can be pushed according to the head leader and/or tail leader of the multimedia file and the pushing flexibility of the promotion information is improved.
Description
[technical field]
The present invention relates to push technology, relate in particular to a kind of method for pushing and device of promotion message.
[background technology]
In recent years, along with the development of Internet technology, risen gradually the Push Service of promotion message, for example, advertisement pushing, game push or apply propelling movement etc.In the process of play multimedia file, for example, after receiving the instruction that starts to play, or after receiving the instruction that suspends broadcasting or stop playing, etc., can push promotion message to user.
But, because promotion message pushes according to playing dependent instruction, thereby cause the reduction of the propelling movement dirigibility of promotion message.
[summary of the invention]
Many aspects of the present invention provide a kind of method for pushing and device of promotion message, in order to improve the propelling movement dirigibility of promotion message.
An aspect of of the present present invention, provides a kind of method for pushing of promotion message, comprising:
Obtain head and/or the corresponding time range of run-out of multimedia file;
According to described time range, in the head of described multimedia file and/or the playing process of run-out, carry out the propelling movement of target promotion message.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described in obtain the head and/or the corresponding time range of run-out of multimedia file before, also comprise:
Obtain pending described multimedia file, described multimedia file comprises at least two two field pictures;
Utilize object tracking technique, described at least two two field pictures are carried out to identifying processing, to obtain file destination fragment;
According to the caption content of described multimedia file and captions time, obtain target subtitle fragment;
According to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, and the described object tracking technique that utilizes, carries out identifying processing to described at least two two field pictures, to obtain file destination fragment, comprising:
Utilize object tracking technique, at least two two field pictures, occur the image of destination object described in extraction, to obtain at least two alternative file fragments;
According to the very first time interval between alternative file fragment adjacent in described at least two alternative file fragments and the very first time threshold value setting in advance, adjacent alternative file fragment is merged to processing, to obtain described file destination fragment.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described according to the caption content of described multimedia file and captions time, obtains target subtitle fragment, comprising:
According to the caption content of described multimedia file and captions time, obtain at least two candidate's subtitle fragment;
According to second time interval between candidate's subtitle fragment adjacent in described at least two candidate's subtitle fragment and the second time threshold setting in advance, adjacent candidate's subtitle fragment is merged to processing, to obtain described target subtitle fragment.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described according to described file destination fragment and described target subtitle fragment, determines head and/or the run-out of described multimedia file, comprising:
According to described file destination fragment and described target subtitle fragment, obtain at least one and merge file fragment;
According to the 3rd time interval between fusion file fragment adjacent in the end time of the start time of described at least one fusion file fragment, described at least one fusion file fragment, described at least one fusion file fragment and the 3rd time threshold setting in advance, determine head and/or the run-out of described multimedia file.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described according to described time range, in the head of described multimedia file and/or the playing process of run-out, before carrying out the propelling movement of target promotion message, also comprises:
Obtain the caption content of described multimedia file;
According to described caption content, obtain candidate's promotion message of mating with described caption content, using as described target promotion message.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described according to described caption content, obtains candidate's promotion message of mating with described caption content, using as described target promotion message, comprising:
Described caption content is carried out to feature extraction, to obtain First Characteristic information;
The text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, to obtain at least one Second Characteristic information;
According to described First Characteristic information and described at least one Second Characteristic information, select at least one candidate's promotion message, using as described target promotion message.
Aspect as above and arbitrary possible implementation, a kind of implementation is further provided, described according to described First Characteristic information and described at least one Second Characteristic information, select at least one candidate's promotion message, using as described target promotion message, comprising:
Calculate the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information;
Select at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance, using as described target promotion message; Or select to be less than or equal at least one the candidate's promotion message under the corresponding Second Characteristic information of distance of pre-configured distance threshold, using as described target promotion message.
Another aspect of the present invention, provides a kind of pusher of promotion message, comprising:
Time acquisition unit, for obtaining head and/or the corresponding time range of run-out of multimedia file;
Push unit, for according to described time range, in the head of described multimedia file and/or the playing process of run-out, carries out the propelling movement of target promotion message.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, and described device also comprises:
File acquisition unit, for obtaining pending described multimedia file, described multimedia file comprises at least two two field pictures;
File processing unit, for utilizing object tracking technique, carries out identifying processing to described at least two two field pictures, to obtain file destination fragment;
Captions processing unit, for according to the caption content of described multimedia file and captions time, obtains target subtitle fragment;
Decision package, for according to described file destination fragment and described target subtitle fragment, determines head and/or the run-out of described multimedia file.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described file processing unit, specifically for
Utilize object tracking technique, at least two two field pictures, occur the image of destination object described in extraction, to obtain at least two alternative file fragments; And
According to the very first time interval between alternative file fragment adjacent in described at least two alternative file fragments and the very first time threshold value setting in advance, adjacent alternative file fragment is merged to processing, to obtain described file destination fragment.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described captions processing unit, specifically for
According to the caption content of described multimedia file and captions time, obtain at least two candidate's subtitle fragment; And
According to second time interval between candidate's subtitle fragment adjacent in described at least two candidate's subtitle fragment and the second time threshold setting in advance, adjacent candidate's subtitle fragment is merged to processing, to obtain described target subtitle fragment.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described decision package, specifically for
According to described file destination fragment and described target subtitle fragment, obtain at least one and merge file fragment; And
According to the 3rd time interval between fusion file fragment adjacent in the end time of the start time of described at least one fusion file fragment, described at least one fusion file fragment, described at least one fusion file fragment and the 3rd time threshold setting in advance, determine head and/or the run-out of described multimedia file.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, and described device also comprises:
Captions acquiring unit, for obtaining the caption content of multimedia file;
Matching unit, for according to described caption content, obtains the candidate's promotion message mating with described caption content, using as described target promotion message.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described matching unit, specifically for
Described caption content is carried out to feature extraction, to obtain First Characteristic information;
The text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, to obtain at least one Second Characteristic information; And
According to described First Characteristic information and described at least one Second Characteristic information, select at least one candidate's promotion message, using as described target promotion message.
Aspect as above and arbitrary possible implementation, further provide a kind of implementation, described matching unit, specifically for
Calculate the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information; And
Select at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance, using as described target promotion message; Or select to be less than or equal at least one the candidate's promotion message under the corresponding Second Characteristic information of distance of pre-configured distance threshold, using as described target promotion message.
As shown from the above technical solution, the embodiment of the present invention is by obtaining head and/or the corresponding time range of run-out of multimedia file, and then according to described time range, in the head of described multimedia file and/or the playing process of run-out, carry out the propelling movement of target promotion message, because head and/or the run-out of multimedia file are all generally the contents of single repetition, the beholder of multimedia file does not pay close attention to this part content, can carry out the propelling movement of target promotion message according to the head of multimedia file and/or run-out, thereby improve the propelling movement dirigibility of promotion message.
In addition, adopt technical scheme provided by the invention, because head and/or the run-out of multimedia file are all generally the contents of single repetition, the beholder of multimedia file does not pay close attention to this part content, therefore, carry out the propelling movement of target promotion message according to the head of multimedia file and/or run-out, can effectively improve the utilization factor of multimedia file.
In addition, adopt technical scheme provided by the invention, by obtaining the caption content of multimedia file, and then according to described caption content, obtain the candidate's promotion message mating with described caption content, using as described target promotion message, make it possible in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, can cause that beholder's the interest of video file is to carry out further operation behavior to promotion message, for example, click, the operation behaviors such as registration and purchase, can ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
In addition, adopt technical scheme provided by the invention, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, the beholder's of video file anxious state of mind can be met, satisfaction and the correlativity of promotion message can be effectively improved.
In addition, adopt technical scheme provided by the invention, without artificial participation, can realize the automatic propelling movement of promotion message, therefore, can effectively improve the propelling movement cost of promotion message.
In addition, adopt technical scheme provided by the invention, by utilizing object tracking technique, at least two two field pictures included to determined multimedia file carry out identifying processing, to obtain file destination fragment, and according to the caption content of determined multimedia file and captions time, obtain target subtitle fragment, make it possible to according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file, without operating personnel's Attended Operation process, simple to operate, and accuracy is high, thereby efficiency and the reliability of head and/or run-out identification are improved.
In addition, adopt technical scheme provided by the invention, without operating personnel's Attended Operation process, can realize the automatic identification of head and/or run-out, therefore, can effectively improve the identification cost of head and/or run-out.
[brief description of the drawings]
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
The schematic flow sheet of the method for pushing of the promotion message that Fig. 1 provides for one embodiment of the invention;
The schematic flow sheet of the method for pushing of the promotion message that Fig. 2 provides for another embodiment of the present invention;
The schematic flow sheet of the method for pushing of the promotion message that Fig. 3 provides for another embodiment of the present invention;
The structural representation of the pusher of the promotion message that Fig. 4 provides for another embodiment of the present invention;
The structural representation of the pusher of the promotion message that Fig. 5 provides for another embodiment of the present invention;
The structural representation of the pusher of the promotion message that Fig. 6 provides for another embodiment of the present invention.
[embodiment]
For making object, technical scheme and the advantage of the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiment.Based on the embodiment in the present invention, those of ordinary skill in the art, not making whole other embodiment that obtain under creative work prerequisite, belong to the scope of protection of the invention.
It should be noted that, in the embodiment of the present invention, related terminal can include but not limited to mobile phone, personal digital assistant (Personal Digital Assistant, PDA), wireless handheld device, wireless Internet access basis, PC (Personal Computer, PC), portable computer, MP3 player, MP4 player etc.
In addition, term "and/or" herein, is only a kind of incidence relation of describing affiliated partner, and expression can exist three kinds of relations, and for example, A and/or B, can represent: individualism A exists A and B, these three kinds of situations of individualism B simultaneously.In addition, character "/" herein, generally represents that forward-backward correlation is to liking a kind of relation of "or".
The schematic flow sheet of the method for pushing of the promotion message that Fig. 1 provides for one embodiment of the invention, as shown in Figure 1.
101, obtain head and/or the corresponding time range of run-out of multimedia file.
Wherein, multimedia file can include but not limited at least one in audio file and video file, and the present embodiment is not particularly limited this.
102,, according to described time range, in the head of described multimedia file and/or the playing process of run-out, carry out the propelling movement of target promotion message.
It should be noted that, 101 and 102 executive agent can be pusher, can be arranged in local application, or can also be arranged in the server of network side, or also can be arranged in application by partial function, partial function is arranged in server, and the present embodiment does not limit this.
Be understandable that, described application can be the application program of installing in terminal, or can also be a webpage of the browser installed in terminal, as long as can realize the coupling of promotion message, with provide promotion message outwardness form can, the present embodiment is not particularly limited this.
Like this, by obtaining head and/or the corresponding time range of run-out of multimedia file, and then according to described time range, in the head of described multimedia file and/or the playing process of run-out, carry out the propelling movement of target promotion message, because head and/or the run-out of multimedia file are all generally the contents of single repetition, the beholder of multimedia file does not pay close attention to this part content, can carry out the propelling movement of target promotion message according to the head of multimedia file and/or run-out, thereby improve the propelling movement dirigibility of promotion message.
In addition, adopt technical scheme provided by the invention, because head and/or the run-out of multimedia file are all generally the contents of single repetition, the beholder of multimedia file does not pay close attention to this part content, therefore, carry out the propelling movement of target promotion message according to the head of multimedia file and/or run-out, can effectively improve the utilization factor of multimedia file.
The schematic flow sheet of the method for pushing of the promotion message that Fig. 2 provides for another embodiment of the present invention, as shown in Figure 2.Before 101, can further include following steps:
201, obtain pending multimedia file, described multimedia file comprises at least two two field pictures.
202, utilize object tracking technique, described at least two two field pictures are carried out to identifying processing, to obtain file destination fragment.
203,, according to the caption content of described multimedia file and captions time, obtain target subtitle fragment.
204,, according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file.
It should be noted that, 202 and 203 execution does not have fixing order, can first carry out 202, then carry out 203, or can also first carry out 203, then carry out 202, or can also carry out 202 and 203 simultaneously, and the present embodiment is not particularly limited this.
It should be noted that, 201～204 executive agent can be treating apparatus, can be arranged in local application, or can also be arranged in the server of network side, or also can be arranged in application by partial function, partial function is arranged in server, and the present embodiment does not limit this.
Be understandable that, described application can be the application program of installing in terminal, or can also be a webpage of the browser installed in terminal, as long as can realize the processing of multimedia file, with provide multimedia file outwardness form can, the present embodiment is not particularly limited this.
Like this, by utilizing object tracking technique, at least two two field pictures included to determined multimedia file carry out identifying processing, to obtain file destination fragment, and according to the caption content of determined multimedia file and captions time, obtain target subtitle fragment, make it possible to according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file, without operating personnel's Attended Operation process, simple to operate, and accuracy is high, thus improve efficiency and the reliability of head and/or run-out identification.
Alternatively, in one of the present embodiment possible implementation, in 202, treating apparatus specifically can utilize object tracking technique, occurs the image of destination object described in extraction, to obtain at least two alternative file fragments at least two two field pictures.For example, can, by the image of extracted successive frame, form an alternative file fragment.Then, described treating apparatus can be according to the very first time interval between alternative file fragment adjacent in described at least two alternative file fragments and the very first time threshold value setting in advance, adjacent alternative file fragment is merged to processing, to obtain described file destination fragment.
For example, if very first time interval is less than or equal to very first time threshold value, adjacent alternative file fragment can be merged, to obtain a new alternative file fragment.
Or, again for example, if very first time interval is greater than very first time threshold value, can retain adjacent alternative file fragment, until the very first time interval between alternative file fragment and adjacent any other alternative file fragment is all greater than very first time threshold value, can be using this alternative file fragment as a file destination fragment.
Particularly, destination object wherein can include but not limited to face, and correspondingly, described treating apparatus specifically can utilize face tracking technology, and described at least two two field pictures are carried out to identifying processing, to obtain file destination fragment.
In general, the caption content of multimedia file and captions time can be stored in subtitle file, and for example, subtitle file can comprise following content:
00:00:36,136→00:00:36,731
What?must?it?be?like?not?to?be?crippled?by?fear?and?self-loathing；
Wherein, " 00:00:36,136 → 00:00:36,731 " are the captions time, " What must it be like not to be crippled by fear and self-loathing? " for caption content.
Particularly, treating apparatus specifically can be to the subtitle file processing of standardizing, to extract the caption content and the captions time that are comprised in this subtitle file.
Also sometimes, the caption content of multimedia file is not to be stored in subtitle file separately, and it is exactly a part for the content of multimedia file.So, described treating apparatus can also further utilize captions extractive technique of the prior art, extracts caption content and captions time from multimedia file.Wherein, the detailed description of captions extractive technique can, referring to related content of the prior art, repeat no more herein.
Alternatively, in one of the present embodiment possible implementation, in 203, treating apparatus specifically can, according to the caption content of described multimedia file and captions time, obtain at least two candidate's subtitle fragment.Then, described treating apparatus can be according to second time interval between candidate's subtitle fragment adjacent in described at least two candidate's subtitle fragment and the second time threshold setting in advance, adjacent candidate's subtitle fragment is merged to processing, to obtain described target subtitle fragment.
For example, if second time interval was less than or equal to the second time threshold, adjacent candidate's subtitle fragment can be merged, to obtain new candidate's subtitle fragment.
Or, again for example, if second interval greater than the second time threshold, can retain adjacent candidate's subtitle fragment, until second time interval between candidate's subtitle fragment and adjacent any other candidate's subtitle fragment be all greater than the second time threshold, can be using this candidate's subtitle fragment as a target subtitle fragment.
Alternatively, in one of the present embodiment possible implementation, in 204, treating apparatus specifically can be according to described file destination fragment and described target subtitle fragment, obtains at least one and merges file fragment.
For example, described treating apparatus specifically can be according to the corresponding very first time scope of file destination fragment, with corresponding the second time range of target subtitle fragment, determine the file destination fragment and the target subtitle fragment that between very first time scope and the second time range, there are common factor, by the multimedia file fragment within the corresponding time range of this target subtitle fragment, with this file destination fragment, merge, merge file fragment to obtain one.For example, very first time scope is 5～10s, and the second time range is 8～15s, and merging file fragment can be the corresponding file fragment of time range 5～15s.
Then, described treating apparatus can according to described at least one merge start time of file fragment be first start time of merging file fragment, described at least one end time of merging file fragment are last end time of merging file fragment, described at least one merge the 3rd time interval between fusion file fragment adjacent in file fragment and the 3rd time threshold setting in advance, determine head and/or the run-out of described multimedia file.
For example, if start time, end time or the 3rd time interval are less than or equal to the 3rd time threshold, can ignore this start time, end time or the 3rd time interval.
Or, again for example, if at least one item in start time, end time and the 3rd time interval, be greater than the 3rd time threshold, can determine at least one in time range corresponding to time range after time range, the end time before the start time and the 3rd time interval, head and/or run-out that interior multimedia file fragment is described multimedia file.
Be understandable that, treating apparatus is specifically defined as a multimedia file fragment head of multimedia file, or the run-out of multimedia file, can be according to the time interval between this corresponding start time of multimedia file fragment and the start time of multimedia file, and time interval between this corresponding end time of multimedia file fragment and the end time of multimedia file, determine, the present embodiment is not particularly limited this.
In the present embodiment, by utilizing object tracking technique, at least two two field pictures included to determined multimedia file carry out identifying processing, to obtain file destination fragment, and according to the caption content of determined multimedia file and captions time, obtain target subtitle fragment, make it possible to according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file, without operating personnel's Attended Operation process, simple to operate, and accuracy is high, thus improve efficiency and the reliability of head and/or run-out identification.
In addition, adopt technical scheme provided by the invention, without operating personnel's Attended Operation process, can realize the automatic identification of head and/or run-out, therefore, can effectively improve the identification cost of head and/or run-out.
The schematic flow sheet of the method for pushing of the promotion message that Fig. 3 provides for another embodiment of the present invention, as shown in Figure 3.Before 102, can further include following steps:
301, obtain the caption content of multimedia file.
302,, according to described caption content, obtain candidate's promotion message of mating with described caption content, using as described target promotion message.
Like this, by obtaining the caption content of multimedia file, and then according to described caption content, obtain the candidate's promotion message mating with described caption content, using as described target promotion message, make it possible in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, can cause that beholder's the interest of video file is to carry out further operation behavior to promotion message, for example, click, the operation behaviors such as registration and purchase, can ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
Alternatively, in one of the present embodiment possible implementation, in 301, pusher specifically can obtain the at the appointed time insider information within scope of multimedia file, or can also obtain the insider information of multimedia file within All Time scope, the present embodiment is not particularly limited this.
In general, the caption content of multimedia file can be stored in subtitle file, comprises captions time and caption content in this subtitle file, and for example, subtitle file can comprise following content:
00:00:36,136→00:00:36,731
What?must?it?be?like?not?to?be?crippled?by?fear?and?self-loathing；
Wherein, " 00:00:36,136 → 00:00:36,731 " are the captions time, " What must it be like not to be crippled by fear and self-loathing? " for caption content.
Particularly, pusher specifically can be to the subtitle file processing of standardizing, to extract the caption content being comprised in this subtitle file.
Also sometimes, the caption content of multimedia file is not to be stored in subtitle file separately, and it is exactly a part for the content of multimedia file.So, described pusher can also further utilize captions extractive technique of the prior art, extracts caption content from multimedia file.Wherein, the detailed description of captions extractive technique can, referring to related content of the prior art, repeat no more herein.
Alternatively, in one of the present embodiment possible implementation, in 302, pusher specifically can carry out feature extraction to described caption content, to obtain First Characteristic information, and the text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, to obtain at least one Second Characteristic information.Then, described pusher can, according to described First Characteristic information and described at least one Second Characteristic information, be selected at least one candidate's promotion message, using as described target promotion message.
Like this, by the excavation of the caption content to multimedia file, and then match corresponding candidate's promotion message, using as described target promotion message, make it possible to push in the playing process of multimedia file, can effectively ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
Particularly, described pusher specifically can calculate the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information.
Then, described pusher can be selected at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance, using as described target promotion message.For example, can be according to distance order from small to large, at least one candidate's promotion message is sorted, and in ranking results, the forward one or more candidate's promotion messages of rank are exactly " at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance ".
Or described pusher can also select to be less than or equal at least one the candidate's promotion message under the corresponding Second Characteristic information of distance of pre-configured distance threshold, using as described target promotion message, the present embodiment is not particularly limited this.
Wherein, the text message of described candidate's promotion message, can be the attribute information of candidate's promotion message, can include but not limited to type; Field; Keyword; Label; And at least one in describing, the present embodiment is not particularly limited this.
Particularly, pusher can adopt arbitrary feature extraction algorithm of the prior art, and the text message of described caption content or candidate's promotion message is carried out to feature extraction, and the present embodiment is not particularly limited this.
For example, pusher can utilize topic model (Latent Dirichlet Allocation, LDA) algorithm, and described caption content is carried out to feature extraction, is proper vector A(a1 to obtain described First Characteristic information, a2, and a3 ..., an); And utilize LDA algorithm, and the text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, is proper vector B(b1 to obtain described at least one Second Characteristic information, b2, and b3 ..., bn).And then, described pusher can calculated characteristics vector A(a1, a2, a3 ..., an) and proper vector B(b1, b2, b3 ..., bn) between distance.Wherein, the detailed description of LDA algorithm can, referring to related content of the prior art, repeat no more herein.
In the present embodiment, by obtaining the caption content of multimedia file, and then according to described caption content, obtain the candidate's promotion message mating with described caption content, using as described target promotion message, make it possible in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, can cause that beholder's the interest of video file is to carry out further operation behavior to promotion message, for example, click, the operation behaviors such as registration and purchase, can ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
In addition, adopt technical scheme provided by the invention, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, the beholder's of video file anxious state of mind can be met, satisfaction and the correlativity of promotion message can be effectively improved.
In addition, adopt technical scheme provided by the invention, without artificial participation, can realize the automatic propelling movement of promotion message, therefore, can effectively improve the propelling movement cost of promotion message.
In addition, adopt technical scheme provided by the invention, without artificial participation, can realize the automatic propelling movement of promotion message, simple to operate, therefore, can effectively improve the pushing efficiency of promotion message.
It should be noted that, for aforesaid each embodiment of the method, for simple description, therefore it is all expressed as to a series of combination of actions, but those skilled in the art should know, the present invention is not subject to the restriction of described sequence of movement, because according to the present invention, some step can adopt other orders or carry out simultaneously.Secondly, those skilled in the art also should know, the embodiment described in instructions all belongs to preferred embodiment, and related action and module might not be that the present invention is necessary.
In the above-described embodiments, the description of each embodiment is all emphasized particularly on different fields, in certain embodiment, there is no the part of detailed description, can be referring to the associated description of other embodiment.
The structural representation of the pusher of the promotion message that Fig. 4 provides for another embodiment of the present invention, as shown in Figure 4.The pusher of the promotion message of the present embodiment can comprise time acquisition unit 41 and push unit 42.Wherein,
Time acquisition unit 41, for obtaining head and/or the corresponding time range of run-out of multimedia file.
Wherein, multimedia file can include but not limited at least one in audio file and video file, and the present embodiment is not particularly limited this.
Push unit 42, for according to described time range, in the head of described multimedia file and/or the playing process of run-out, carries out the propelling movement of target promotion message.
It should be noted that, the pusher of the promotion message that the present embodiment provides can be a pusher, can be arranged in local application, or can also be arranged in the server of network side, or also can be arranged in application by partial function, partial function is arranged in server, and the present embodiment does not limit this.
Be understandable that, described application can be the application program of installing in terminal, or can also be a webpage of the browser installed in terminal, as long as can realize the coupling of promotion message, with provide promotion message outwardness form can, the present embodiment is not particularly limited this.
Like this, obtain head and/or the corresponding time range of run-out of multimedia file by time acquisition unit, and then by push unit according to described time range, in the head of described multimedia file and/or the playing process of run-out, carry out the propelling movement of target promotion message, because head and/or the run-out of multimedia file are all generally the contents of single repetition, the beholder of multimedia file does not pay close attention to this part content, can carry out the propelling movement of target promotion message according to the head of multimedia file and/or run-out, thereby improve the propelling movement dirigibility of promotion message.
In addition, adopt technical scheme provided by the invention, because head and/or the run-out of multimedia file are all generally the contents of single repetition, the beholder of multimedia file does not pay close attention to this part content, therefore, carry out the propelling movement of target promotion message according to the head of multimedia file and/or run-out, can effectively improve the utilization factor of multimedia file.
The structural representation of the pusher of the promotion message that Fig. 5 provides for another embodiment of the present invention, as shown in Figure 5.The pusher of the promotion message of the present embodiment can further include file acquisition unit 51, file processing unit 52, captions processing unit 53 and decision package 54.Wherein,
File acquisition unit 51, for obtaining pending multimedia file, described multimedia file comprises at least two two field pictures.
File processing unit 52, for utilizing object tracking technique, carries out identifying processing to described at least two two field pictures, to obtain file destination fragment.
Captions processing unit 53, for according to the caption content of described multimedia file and captions time, obtains target subtitle fragment.
Decision package 54, for according to described file destination fragment and described target subtitle fragment, determines head and/or the run-out of described multimedia file.
Like this, by file processing unit by using object tracking technique, at least two two field pictures included to the determined multimedia file in file acquisition unit carry out identifying processing, to obtain file destination fragment, and captions processing unit is according to the caption content of the determined multimedia file in file acquisition unit and captions time, obtain target subtitle fragment, make the decision package can be according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file, without operating personnel's Attended Operation process, simple to operate, and accuracy is high, thereby efficiency and the reliability of head and/or run-out identification are improved.
Alternatively, in one of the present embodiment possible implementation, described file processing unit 52, specifically can be for utilizing object tracking technique, described in extraction, at least two two field pictures, there is the image of destination object, for example, to obtain at least two alternative file fragments,, can, by the image of extracted successive frame, form an alternative file fragment; And according to the very first time interval between alternative file fragment adjacent in described at least two alternative file fragments and the very first time threshold value setting in advance, adjacent alternative file fragment is merged to processing, to obtain described file destination fragment.
For example, if very first time interval is less than or equal to very first time threshold value, 52 of described file processing unit can merge adjacent alternative file fragment, to obtain a new alternative file fragment.
Or, again for example, if very first time interval is greater than very first time threshold value, 52 of described file processing unit can retain adjacent alternative file fragment, until the very first time interval between alternative file fragment and adjacent any other alternative file fragment is all greater than very first time threshold value, 52 of described file processing unit can be using this alternative file fragment as a file destination fragment.
Particularly, destination object wherein can include but not limited to face, and correspondingly, described file processing unit 52 specifically can utilize face tracking technology, and described at least two two field pictures are carried out to identifying processing, to obtain file destination fragment.
In general, the caption content of multimedia file and captions time can be stored in subtitle file, and for example, subtitle file can comprise following content:
00:00:36,136→00:00:36,731
What?must?it?be?like?not?to?be?crippled?by?fear?and?self-loathing；
Wherein, " 00:00:36,136 → 00:00:36,731 " are the captions time, " What must it be like not to be crippled by fear and self-loathing? " for caption content.
Particularly, described file processing unit 52 can be to the subtitle file processing of standardizing, to extract the caption content and the captions time that are comprised in this subtitle file.
Also sometimes, the caption content of multimedia file is not to be stored in subtitle file separately, and it is exactly a part for the content of multimedia file.So, described file processing unit 52 can also further utilize captions extractive technique of the prior art, extracts caption content and captions time from multimedia file.Wherein, the detailed description of captions extractive technique can, referring to related content of the prior art, repeat no more herein.
Alternatively, in one of the present embodiment possible implementation, described captions processing unit 53, specifically can, for according to the caption content of described multimedia file and captions time, obtain at least two candidate's subtitle fragment; And according to second time interval between candidate's subtitle fragment adjacent in described at least two candidate's subtitle fragment and the second time threshold setting in advance, adjacent candidate's subtitle fragment is merged to processing, to obtain described target subtitle fragment.
For example, if second time interval was less than or equal to the second time threshold, 53 of described captions processing units can merge adjacent candidate's subtitle fragment, to obtain new candidate's subtitle fragment.
Or, again for example, if second interval greater than the second time threshold, 53 of described captions processing units can retain adjacent candidate's subtitle fragment, until second time interval between candidate's subtitle fragment and adjacent any other candidate's subtitle fragment is all greater than the second time threshold, 53 of described captions processing units can be using this candidate's subtitle fragment as a target subtitle fragment.
Alternatively, in one of the present embodiment possible implementation, described decision package 54, specifically can be for according to described file destination fragment and described target subtitle fragment, obtain at least one and merge file fragment, for example, described decision package 54 specifically can be according to the corresponding very first time scope of file destination fragment, with corresponding the second time range of target subtitle fragment, determine the file destination fragment and the target subtitle fragment that between very first time scope and the second time range, there are common factor, by the multimedia file fragment within the corresponding time range of this target subtitle fragment, with this file destination fragment, merge, merge file fragment to obtain one, for example, very first time scope is 5～10s, the second time range is 8～15s, merging file fragment can be the corresponding file fragment of time range 5～15s, and according to the 3rd time interval between fusion file fragment adjacent in the end time of the start time of described at least one fusion file fragment, described at least one fusion file fragment, described at least one fusion file fragment and the 3rd time threshold setting in advance, determine head and/or the run-out of described multimedia file.
For example, if start time, end time or the 3rd time interval are less than or equal to the 3rd time threshold, 54 of described decision packages can be ignored this start time, end time or the 3rd time interval.
Or, again for example, if at least one item in start time, end time and the 3rd time interval, be greater than the 3rd time threshold, 54 of described decision packages can be determined at least one in time range after time range, the end time before the start time and time range corresponding to the 3rd time interval, head and/or run-out that interior multimedia file fragment is described multimedia file.
Be understandable that, described decision package 54 is specifically defined as a multimedia file fragment head of multimedia file, or the run-out of multimedia file, can be according to the time interval between this corresponding start time of multimedia file fragment and the start time of multimedia file, and time interval between this corresponding end time of multimedia file fragment and the end time of multimedia file, determine, the present embodiment is not particularly limited this.
In the present embodiment, by file processing unit by using object tracking technique, at least two two field pictures included to the determined multimedia file in file acquisition unit carry out identifying processing, to obtain file destination fragment, and captions processing unit is according to the caption content of the determined multimedia file in file acquisition unit and captions time, obtain target subtitle fragment, make the decision package can be according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file, without operating personnel's Attended Operation process, simple to operate, and accuracy is high, thereby efficiency and the reliability of head and/or run-out identification are improved.
In addition, adopt technical scheme provided by the invention, without operating personnel's Attended Operation process, can realize the automatic identification of head and/or run-out, therefore, can effectively improve the identification cost of head and/or run-out.
The structural representation of the pusher of the promotion message that Fig. 6 provides for another embodiment of the present invention, as shown in Figure 6.The pusher of the promotion message of the present embodiment can further include captions acquiring unit 61 and matching unit 62.Wherein,
Captions acquiring unit 61, for obtaining the caption content of multimedia file.
Matching unit 62, for according to described caption content, obtains the candidate's promotion message mating with described caption content, using as described target promotion message.
Like this, obtain the caption content of multimedia file by captions acquiring unit, and then by matching unit according to described caption content, obtain the candidate's promotion message mating with described caption content, using as described target promotion message, make it possible in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, can cause that beholder's the interest of video file is to carry out further operation behavior to promotion message, for example, click, the operation behaviors such as registration and purchase, can ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
Alternatively, in one of the present embodiment possible implementation, described captions acquiring unit 61, specifically can obtain the at the appointed time insider information within scope of multimedia file, or can also obtain the insider information of multimedia file within All Time scope, the present embodiment is not particularly limited this.
In general, the caption content of multimedia file can be stored in subtitle file, comprises captions time and caption content in this subtitle file, and for example, subtitle file can comprise following content:
00:00:36,136→00:00:36,731
What?must?it?be?like?not?to?be?crippled?by?fear?and?self-loathing；
Wherein, " 00:00:36,136 → 00:00:36,731 " are the captions time, " What must it be like not to be crippled by fear and self-loathing? " for caption content.
Particularly, described captions acquiring unit 61 specifically can be to the subtitle file processing of standardizing, to extract the caption content being comprised in this subtitle file.
Also sometimes, the caption content of multimedia file is not to be stored in subtitle file separately, and it is exactly a part for the content of multimedia file.So, described captions acquiring unit 61 can also further utilize captions extractive technique of the prior art, extracts caption content from multimedia file.Wherein, the detailed description of captions extractive technique can, referring to related content of the prior art, repeat no more herein.
Alternatively, in one of the present embodiment possible implementation, described matching unit 62, specifically can be for described caption content is carried out to feature extraction, to obtain First Characteristic information; The text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, to obtain at least one Second Characteristic information; And according to described First Characteristic information and described at least one Second Characteristic information, select at least one candidate's promotion message, using as described target promotion message.
Like this, by the excavation of the caption content to multimedia file, and then match corresponding candidate's promotion message, using as described target promotion message, make it possible to push in the playing process of multimedia file, can effectively ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
Particularly, described matching unit 62, specifically can be for calculating the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information; And select at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance, using as described target promotion message.For example, can be according to distance order from small to large, at least one candidate's promotion message is sorted, and in ranking results, the forward one or more candidate's promotion messages of rank are exactly " at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance ".
Particularly, described matching unit 62, specifically can be for calculating the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information; And select to be less than or equal at least one the candidate's promotion message under the corresponding Second Characteristic information of distance of pre-configured distance threshold, using as described target promotion message.
Wherein, the text message of described candidate's promotion message, can be the attribute information of candidate's promotion message, can include but not limited to type; Field; Keyword; Label; And at least one in describing, the present embodiment is not particularly limited this.
Particularly, described matching unit 62 can adopt arbitrary feature extraction algorithm of the prior art, and the text message of described caption content or candidate's promotion message is carried out to feature extraction, and the present embodiment is not particularly limited this.
For example, described matching unit 62 can utilize LDA algorithm, and described caption content is carried out to feature extraction, is proper vector A(a1 to obtain described First Characteristic information, a2, and a3 ..., an); And utilize LDA algorithm, and the text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, is proper vector B(b1 to obtain described at least one Second Characteristic information, b2, and b3 ..., bn).And then, can calculated characteristics vector A(a1, a2, a3 ..., an) and proper vector B(b1, b2, b3 ..., bn) between distance.Wherein, the detailed description of LDA algorithm can, referring to related content of the prior art, repeat no more herein.
In the present embodiment, obtain the caption content of multimedia file by captions acquiring unit, and then by matching unit according to described caption content, obtain the candidate's promotion message mating with described caption content, using as described target promotion message, make it possible in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, can cause that beholder's the interest of video file is to carry out further operation behavior to promotion message, for example, click, the operation behaviors such as registration and purchase, can ensure the accurate propelling movement of promotion message, thereby improve the conversion ratio of promotion message.
In addition, adopt technical scheme provided by the invention, because target promotion message is the promotion message mating with the caption content of multimedia file, therefore, in the playing process of described multimedia file, carry out the propelling movement of described target promotion message, the beholder's of video file anxious state of mind can be met, satisfaction and the correlativity of promotion message can be effectively improved.
In addition, adopt technical scheme provided by the invention, without artificial participation, can realize the automatic propelling movement of promotion message, therefore, can effectively improve the propelling movement cost of promotion message.
In addition, adopt technical scheme provided by the invention, without artificial participation, can realize the automatic propelling movement of promotion message, simple to operate, therefore, can effectively improve the pushing efficiency of promotion message.
Those skilled in the art can be well understood to, for convenience and simplicity of description, the system of foregoing description, the specific works process of device and unit, can, with reference to the corresponding process in preceding method embodiment, not repeat them here.
In several embodiment provided by the present invention, should be understood that, disclosed system, apparatus and method, can realize by another way.For example, device embodiment described above is only schematic, for example, the division of described unit, be only that a kind of logic function is divided, when actual realization, can have other dividing mode, for example multiple unit or assembly can in conjunction with or can be integrated into another system, or some features can ignore, or do not carry out.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, indirect coupling or the communication connection of device or unit can be electrically, machinery or other form.
The described unit as separating component explanation can or can not be also physically to separate, and the parts that show as unit can be or can not be also physical locations, can be positioned at a place, or also can be distributed in multiple network element.Can select according to the actual needs some or all of unit wherein to realize the object of the present embodiment scheme.
In addition, the each functional unit in each embodiment of the present invention can be integrated in a processing unit, can be also that the independent physics of unit exists, and also can be integrated in a unit two or more unit.Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that also can adopt hardware to add SFU software functional unit realizes.
The integrated unit that the above-mentioned form with SFU software functional unit realizes, can be stored in a computer read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, comprise that some instructions (can be personal computers in order to make a computer installation, server, or network equipment etc.) or processor (processor) carry out the part steps of method described in each embodiment of the present invention.And aforesaid storage medium comprises: various media that can be program code stored such as USB flash disk, portable hard drive, ROM (read-only memory) (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CDs.
Finally it should be noted that: above embodiment only, in order to technical scheme of the present invention to be described, is not intended to limit; Although the present invention is had been described in detail with reference to previous embodiment, those of ordinary skill in the art is to be understood that: its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement; And these amendments or replacement do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (16)
1. a disposal route for promotion message, is characterized in that, comprising:
Obtain head and/or the corresponding time range of run-out of multimedia file;
According to described time range, in the head of described multimedia file and/or the playing process of run-out, carry out the propelling movement of target promotion message.
2. method according to claim 1, is characterized in that, described in obtain the head and/or the corresponding time range of run-out of multimedia file before, also comprise:
Obtain pending described multimedia file, described multimedia file comprises at least two two field pictures;
Utilize object tracking technique, described at least two two field pictures are carried out to identifying processing, to obtain file destination fragment;
According to the caption content of described multimedia file and captions time, obtain target subtitle fragment;
According to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file.
3. method according to claim 2, is characterized in that, the described object tracking technique that utilizes, carries out identifying processing to described at least two two field pictures, to obtain file destination fragment, comprising:
Utilize object tracking technique, at least two two field pictures, occur the image of destination object described in extraction, to obtain at least two alternative file fragments;
According to the very first time interval between alternative file fragment adjacent in described at least two alternative file fragments and the very first time threshold value setting in advance, adjacent alternative file fragment is merged to processing, to obtain described file destination fragment.
4. method according to claim 2, is characterized in that, described according to the caption content of described multimedia file and captions time, obtains target subtitle fragment, comprising:
According to the caption content of described multimedia file and captions time, obtain at least two candidate's subtitle fragment;
According to second time interval between candidate's subtitle fragment adjacent in described at least two candidate's subtitle fragment and the second time threshold setting in advance, adjacent candidate's subtitle fragment is merged to processing, to obtain described target subtitle fragment.
5. according to the method described in the arbitrary claim of claim 2～4, it is characterized in that, described according to described file destination fragment and described target subtitle fragment, determine head and/or the run-out of described multimedia file, comprising:
According to described file destination fragment and described target subtitle fragment, obtain at least one and merge file fragment;
According to the 3rd time interval between fusion file fragment adjacent in the end time of the start time of described at least one fusion file fragment, described at least one fusion file fragment, described at least one fusion file fragment and the 3rd time threshold setting in advance, determine head and/or the run-out of described multimedia file.
6. method according to claim 1, is characterized in that, described according to described time range, in the head of described multimedia file and/or the playing process of run-out, before carrying out the propelling movement of target promotion message, also comprises:
Obtain the caption content of described multimedia file;
According to described caption content, obtain candidate's promotion message of mating with described caption content, using as described target promotion message.
7. method according to claim 6, is characterized in that, described according to described caption content, obtains candidate's promotion message of mating with described caption content, using as described target promotion message, comprising:
Described caption content is carried out to feature extraction, to obtain First Characteristic information;
The text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, to obtain at least one Second Characteristic information;
According to described First Characteristic information and described at least one Second Characteristic information, select at least one candidate's promotion message, using as described target promotion message.
8. method according to claim 7, is characterized in that, describedly selects at least one candidate's promotion message according to described First Characteristic information and described at least one Second Characteristic information, using as described target promotion message, comprising:
Calculate the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information;
Select at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance, using as described target promotion message; Or select to be less than or equal at least one the candidate's promotion message under the corresponding Second Characteristic information of distance of pre-configured distance threshold, using as described target promotion message.
9. a treating apparatus for promotion message, is characterized in that, comprising:
Time acquisition unit, for obtaining head and/or the corresponding time range of run-out of multimedia file;
Push unit, for according to described time range, in the head of described multimedia file and/or the playing process of run-out, carries out the propelling movement of target promotion message.
10. device according to claim 9, is characterized in that, described device also comprises:
File acquisition unit, for obtaining pending described multimedia file, described multimedia file comprises at least two two field pictures;
File processing unit, for utilizing object tracking technique, carries out identifying processing to described at least two two field pictures, to obtain file destination fragment;
Captions processing unit, for according to the caption content of described multimedia file and captions time, obtains target subtitle fragment;
Decision package, for according to described file destination fragment and described target subtitle fragment, determines head and/or the run-out of described multimedia file.
11. devices according to claim 9, is characterized in that, described file processing unit, specifically for
Utilize object tracking technique, at least two two field pictures, occur the image of destination object described in extraction, to obtain at least two alternative file fragments; And
According to the very first time interval between alternative file fragment adjacent in described at least two alternative file fragments and the very first time threshold value setting in advance, adjacent alternative file fragment is merged to processing, to obtain described file destination fragment.
12. devices according to claim 9, is characterized in that, described captions processing unit, specifically for
According to the caption content of described multimedia file and captions time, obtain at least two candidate's subtitle fragment; And
According to second time interval between candidate's subtitle fragment adjacent in described at least two candidate's subtitle fragment and the second time threshold setting in advance, adjacent candidate's subtitle fragment is merged to processing, to obtain described target subtitle fragment.
13. according to the device described in the arbitrary claim of claim 9～12, it is characterized in that, and described decision package, specifically for
According to described file destination fragment and described target subtitle fragment, obtain at least one and merge file fragment; And
According to the 3rd time interval between fusion file fragment adjacent in the end time of the start time of described at least one fusion file fragment, described at least one fusion file fragment, described at least one fusion file fragment and the 3rd time threshold setting in advance, determine head and/or the run-out of described multimedia file.
14. devices according to claim 9, is characterized in that, described device also comprises:
Captions acquiring unit, for obtaining the caption content of multimedia file;
Matching unit, for according to described caption content, obtains the candidate's promotion message mating with described caption content, using as described target promotion message.
15. devices according to claim 9, is characterized in that, described matching unit, specifically for
Described caption content is carried out to feature extraction, to obtain First Characteristic information;
The text message for the treatment of at least one candidate's promotion message of propelling movement carries out feature extraction, to obtain at least one Second Characteristic information; And
According to described First Characteristic information and described at least one Second Characteristic information, select at least one candidate's promotion message, using as described target promotion message.
16. devices according to claim 15, is characterized in that, described matching unit, specifically for
Calculate the distance between each Second Characteristic information in described First Characteristic information and described at least one Second Characteristic information; And
Select at least one the candidate's promotion message under the minimum corresponding Second Characteristic information of at least one distance, using as described target promotion message; Or select to be less than or equal at least one the candidate's promotion message under the corresponding Second Characteristic information of distance of pre-configured distance threshold, using as described target promotion message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410148385.6A CN103984699B (en) | 2014-04-14 | 2014-04-14 | The method for pushing and device of promotion message |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410148385.6A CN103984699B (en) | 2014-04-14 | 2014-04-14 | The method for pushing and device of promotion message |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103984699A true CN103984699A (en) | 2014-08-13 |
| CN103984699B CN103984699B (en) | 2018-05-04 |
Family
ID=51276672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410148385.6A Active CN103984699B (en) | 2014-04-14 | 2014-04-14 | The method for pushing and device of promotion message |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103984699B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268168A (en) * | 2014-09-10 | 2015-01-07 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information to user |
| CN104883608A (en) * | 2015-06-19 | 2015-09-02 | 北京酷云互动科技有限公司 | Push method and push system |
| CN107431828A (en) * | 2015-02-24 | 2017-12-01 | 拍搜有限公司 | For identifying the method and system of relevant media content |
| CN111970563A (en) * | 2020-08-28 | 2020-11-20 | 维沃移动通信有限公司 | Video processing method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201134821Y (en) * | 2007-11-19 | 2008-10-15 | 刘海波 | Multimedia playing system capable of advertisement insertion |
| CN101345853A (en) * | 2008-08-07 | 2009-01-14 | 深圳市迅雷网络技术有限公司 | Method and system for acquiring video resource cutting time point |
| CN101668194A (en) * | 2008-09-05 | 2010-03-10 | 中兴通讯股份有限公司 | Method and device for inserting and playing advertisement based on content fragmentation |
| CN102075695A (en) * | 2010-12-30 | 2011-05-25 | 中国科学院自动化研究所 | New generation intelligent cataloging system and method facing large amount of broadcast television programs |
| CN103336955A (en) * | 2013-07-09 | 2013-10-02 | 百度在线网络技术（北京）有限公司 | Generation method and generation device of character playing locus in video, and client |
| CN103442001A (en) * | 2013-08-22 | 2013-12-11 | 百度在线网络技术（北京）有限公司 | Information recommendation method, device and server |
-
2014
- 2014-04-14 CN CN201410148385.6A patent/CN103984699B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201134821Y (en) * | 2007-11-19 | 2008-10-15 | 刘海波 | Multimedia playing system capable of advertisement insertion |
| CN101345853A (en) * | 2008-08-07 | 2009-01-14 | 深圳市迅雷网络技术有限公司 | Method and system for acquiring video resource cutting time point |
| CN101668194A (en) * | 2008-09-05 | 2010-03-10 | 中兴通讯股份有限公司 | Method and device for inserting and playing advertisement based on content fragmentation |
| CN102075695A (en) * | 2010-12-30 | 2011-05-25 | 中国科学院自动化研究所 | New generation intelligent cataloging system and method facing large amount of broadcast television programs |
| CN103336955A (en) * | 2013-07-09 | 2013-10-02 | 百度在线网络技术（北京）有限公司 | Generation method and generation device of character playing locus in video, and client |
| CN103442001A (en) * | 2013-08-22 | 2013-12-11 | 百度在线网络技术（北京）有限公司 | Information recommendation method, device and server |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268168A (en) * | 2014-09-10 | 2015-01-07 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information to user |
| CN107431828A (en) * | 2015-02-24 | 2017-12-01 | 拍搜有限公司 | For identifying the method and system of relevant media content |
| CN107431828B (en) * | 2015-02-24 | 2020-03-13 | 拍搜有限公司 | Method and system for identifying related media content |
| US10715862B2 (en) | 2015-02-24 | 2020-07-14 | Visenze Pte Ltd | Method and system for identifying relevant media content |
| US10779037B2 (en) | 2015-02-24 | 2020-09-15 | Visenze Pte Ltd | Method and system for identifying relevant media content |
| CN104883608A (en) * | 2015-06-19 | 2015-09-02 | 北京酷云互动科技有限公司 | Push method and push system |
| CN104883608B (en) * | 2015-06-19 | 2019-04-16 | 北京酷云互动科技有限公司 | A kind of method for pushing and supplying system |
| CN111970563A (en) * | 2020-08-28 | 2020-11-20 | 维沃移动通信有限公司 | Video processing method and device and electronic equipment |
| CN111970563B (en) * | 2020-08-28 | 2022-03-04 | 维沃移动通信有限公司 | Video processing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103984699B (en) | 2018-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111143610B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN110378732B (en) | Information display method, information association method, device, equipment and storage medium | |
| US11288727B2 (en) | Content creation suggestions using failed searches and uploads | |
| CN112511854B (en) | Live video highlight generation method, device, medium and equipment | |
| CN109275047B (en) | Video information processing method and device, electronic equipment and storage medium | |
| CN108509611B (en) | Method and device for pushing information | |
| US11405447B2 (en) | Method, apparatus and system for presenting mobile media information | |
| CN104023271A (en) | Advertisement information pushing method and user equipment | |
| CN104065977A (en) | Audio/video file processing method and device | |
| US20170053365A1 (en) | Content Creation Suggestions using Keywords, Similarity, and Social Networks | |
| CN103500212A (en) | Multi-media file recommending method and electronic device | |
| CN111770375B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN104823183A (en) | Feature-based candidate selection | |
| CN112866790A (en) | Video playing method and system | |
| US20170171334A1 (en) | Single-account multiple-preference recommendation method for video website and electronic device | |
| CN104267922A (en) | Information processing method and electronic equipment | |
| CN105302906A (en) | Information labeling method and apparatus | |
| CN103984699A (en) | Pushing method and pushing device for promotion information | |
| CN103607642A (en) | On demand method of multimedia program and electronic equipment | |
| CN103986981A (en) | Recognition method and device of scenario segments of multimedia files | |
| CN111753131A (en) | Expression package generation method and device, electronic device and medium | |
| CN103731737A (en) | Video information updating method and electronic device | |
| CN103971268A (en) | Method and device for processing promotional information | |
| CN103399737A (en) | Multimedia processing method and device based on voice data | |
| KR102439652B1 (en) | Method and system for providing online customized advertisements based on related posts made after the broadcasting time of broadcasting contents |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |