CN105227973A - Based on information recommendation method and the device of scene Recognition - Google Patents
Based on information recommendation method and the device of scene Recognition Download PDFInfo
- Publication number
- CN105227973A CN105227973A CN201410300737.5A CN201410300737A CN105227973A CN 105227973 A CN105227973 A CN 105227973A CN 201410300737 A CN201410300737 A CN 201410300737A CN 105227973 A CN105227973 A CN 105227973A
- Authority
- CN
- China
- Prior art keywords
- scene characteristic
- scene
- video flowing
- recommendation
- characteristic
- 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
- G06F18/00—Pattern recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
Abstract
The invention discloses a kind of information recommendation method based on scene Recognition and device, wherein, based on the information recommendation method of scene Recognition, comprising: video flowing is mated with the scene characteristic preset, obtains the scene characteristic that described video flowing is corresponding; According to the corresponding relation of scene characteristic and recommendation information, obtain the recommendation information that described video flowing is corresponding; And, present the recommendation information that described video flowing is corresponding.By the present invention, improve the accuracy of information recommendation, can realize according to video scene recommendation information.
Description
Technical field
The present invention relates to the communications field, in particular to a kind of information recommendation method based on scene Recognition and device.
Background technology
At present, at IPTV (InternetProtocolTelevision, referred to as IPTV)/based on the Video service (OverTheTopTV of open the Internet, referred to as OTT-TV) in system, traditional business recommended (as advertisement, shopping) or be directly at electronic program guides (ElectronicProgramGuide, referred to as EPG) configuration service recommended links is recommended on interface, and user enters into the concrete page could watch recommendation information; Be push recommendation information on EPG interface by some message systems, right place shows terminal use.
But these are business recommended is all relatively independent, operating as independently form of service, pushed may be the recommendation information that some users are not interested in.
Summary of the invention
For the inaccurate problem of information recommendation in correlation technique, the invention provides a kind of information recommendation method based on scene Recognition and device, at least to solve the problem.
According to an aspect of the present invention, provide a kind of information recommendation method based on scene Recognition, comprising: video flowing is mated with the scene characteristic preset, obtains the scene characteristic that described video flowing is corresponding; According to the corresponding relation of scene characteristic and recommendation information, obtain the recommendation information that described video flowing is corresponding.
Preferably, video flowing is mated with the scene characteristic preset, comprising: described video flowing is encoded, obtain feature object to be matched; Mated with scene characteristic object by described feature object to be matched, obtain the scene characteristic that described video flowing is corresponding, wherein, described scene characteristic object obtains by encoding to described default scene characteristic in advance.
Preferably, described feature object to be matched is mated with scene characteristic object, obtains the scene characteristic that described video flowing is corresponding, comprising: described feature object to be matched is mated with described scene characteristic object; If the similarity of described feature object to be matched and described scene characteristic object meets pre-conditioned, using scene characteristic corresponding for described scene characteristic object as scene characteristic corresponding to described video flowing.
Preferably, in advance to described default scene characteristic coding, comprising: according to the scene mode that described default scene characteristic is corresponding, classify and described default scene characteristic encoded.
Preferably, the scene mode of described default scene characteristic comprise following one of at least: video scene, voice scene, captions scene, story of a play or opera scene.
Preferably, the form of described default scene characteristic comprise following one of at least: picture, text, voice.
Preferably, described default scene characteristic, comprising: the first scene characteristic and/or the second scene characteristic, and wherein, described first scene characteristic is general scene characteristic, and described second scene characteristic is the special scene characteristic of described video flowing.
Preferably, present the recommendation information that described video flowing is corresponding, comprising: present recommendation information corresponding to described video flowing in the time of presetting.
Preferably, also comprise, present the recommendation information that described video flowing is corresponding.
Preferably, described video flowing is the video flowing to be played of buffer memory, and the recommendation information presenting described video flowing corresponding comprises: when playing described video flowing, present the recommendation information that described video flowing is corresponding.
Preferably, described recommendation information is provided with recommendation identification code, and described recommendation identification code is for distinguishing recommendation information; The corresponding relation of described scene characteristic and recommendation information is scene characteristic and the corresponding relation recommending identification code.
According to a further aspect of the invention, providing a kind of information recommending apparatus based on scene Recognition, comprising: matching module, for being mated with the scene characteristic preset by video flowing, obtaining the scene characteristic that described video flowing is corresponding; Acquisition module, for the corresponding relation according to scene characteristic and recommendation information, obtains the recommendation information that described video flowing is corresponding.
Preferably, described matching module, comprising: coding unit, for encoding to described video flowing, obtains feature object to be matched; Matching unit, for being mated with scene characteristic object by described feature object to be matched, obtains the scene characteristic that described video flowing is corresponding, and wherein, described scene characteristic object obtains by encoding to described default scene characteristic in advance.
Preferably, described coding unit, also for according to scene mode corresponding to described default scene characteristic, classifies and to encode to described default scene characteristic, obtain described scene characteristic object.
Preferably, the scene mode of described default scene characteristic comprise following one of at least: video scene, voice scene, captions scene, story of a play or opera scene.
Preferably, the form of described default scene characteristic comprise following one of at least: picture, text, voice.
Preferably, described default scene characteristic, comprising: the first scene characteristic and/or the second scene characteristic, and wherein, described first scene characteristic is general scene characteristic, and described second scene characteristic is the special scene characteristic of described video flowing.
Preferably, module is presented, for presenting recommendation information corresponding to described video flowing in the time of presetting described in.
Preferably, also comprise: present module, for presenting recommendation information corresponding to described video flowing
Preferably, described video flowing is the video flowing to be played of buffer memory, described in present module, for play described video flowing time, present the recommendation information that described video flowing is corresponding.
Preferably, described recommendation information is provided with recommendation identification code, and described recommendation identification code is for distinguishing recommendation information; The corresponding relation of described scene characteristic and recommendation information is scene characteristic and the corresponding relation recommending identification code.
By the present invention, video flowing is mated with the scene characteristic preset, obtains the scene characteristic that video flowing is corresponding; According to the corresponding relation of scene characteristic and recommendation information, obtain the recommendation information that video flowing is corresponding; And present recommendation information corresponding to video flowing, can recommendation information more accurately based on video scene.
Accompanying drawing explanation
Accompanying drawing described herein is used to provide a further understanding of the present invention, and form a application's part, schematic description and description of the present invention, for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the flow chart one of the information recommendation method based on scene Recognition according to the embodiment of the present invention;
Fig. 2 is the structured flowchart of the information recommending apparatus based on scene Recognition according to the embodiment of the present invention;
Fig. 3 is the flowchart 2 of the information recommendation method based on scene Recognition according to the embodiment of the present invention;
Fig. 4 is the structured flowchart one of the first equipment according to the embodiment of the present invention;
Fig. 5 is the structured flowchart two of the first equipment according to the embodiment of the present invention;
Fig. 6 is the flow chart 3 of the information recommendation method based on scene Recognition according to the embodiment of the present invention;
Fig. 7 is the structured flowchart one of the second equipment according to the embodiment of the present invention;
Fig. 8 is the structured flowchart two of the second equipment according to the embodiment of the present invention;
Fig. 9 is preferably based on the schematic diagram of the information recommendation system of scene Recognition according to the embodiment of the present invention;
Figure 10 is preferably based on the structured flowchart of the information recommendation system of scene Recognition according to the embodiment of the present invention;
Figure 11 is the flow chart issued according to the scene characteristic of the embodiment of the present invention;
Figure 12 is the flow chart generated according to the scene characteristic of the embodiment of the present invention;
Figure 13 is the flow chart mated according to the scene characteristic of the embodiment of the present invention;
Figure 14 is the flow chart of the information recommendation according to the embodiment of the present invention;
Figure 15 is the flow chart of the information recommendation method according to the embodiment of the present invention 1;
Figure 16 is the flow chart of the information recommendation method according to the embodiment of the present invention 2;
Figure 17 is the flow chart of the information recommendation method according to the embodiment of the present invention 3; And
Figure 18 is the flow chart of the information recommendation method according to the embodiment of the present invention 4.
Embodiment
Hereinafter also describe the present invention in detail with reference to accompanying drawing in conjunction with the embodiments.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
In the examples below, the first equipment can be various types of equipment, such as, and Set Top Box, mobile terminal, home server, router etc.The cluster etc. that second equipment can be server, be made up of server.It is contemplated that the method for following examples and device can be realized by computer program.
Fig. 1 is the flow chart one of the information recommendation method based on scene Recognition according to the embodiment of the present invention, and as shown in Figure 1, the method comprising the steps of S102 is to step S104.
Step S102, mates video flowing with the scene characteristic preset, obtains the scene characteristic that this video flowing is corresponding.
Step S104, according to the corresponding relation of scene characteristic and recommendation information, obtains the recommendation information that above-mentioned video flowing is corresponding.
In the embodiment of the present invention, the recommendation information that above-mentioned video flowing is corresponding can also be presented.
In embodiments of the present invention, the scene mode of above-mentioned default scene characteristic can comprise following one of at least: video scene, voice scene, captions scene, story of a play or opera scene.The form of scene characteristic preset can comprise following one of at least: picture, text, voice.
In embodiments of the present invention, above-mentioned scene characteristic is relevant to the content of video, can be video content comprise image, dialogue, the story of a play or opera, performer, film the information such as show time/theme.When user selects to watch certain video, effective Intelligent Recognition is carried out to the scene of video content, and then carry out interaction recommendation according to information such as the image comprised in video content, dialogue, the story of a play or opera, performers, then can well solve the specific aim of recommendation, relevance problem, promote user interactive, really reach and manipulate certain content according to user and just can automatically carry out the concrete business such as recommended advertisements, shopping.
In an execution mode of the embodiment of the present invention, above-mentioned steps S102, can encode to video flowing, obtains feature object to be matched; Mated with scene characteristic object by feature object to be matched, obtain the scene characteristic that video flowing is corresponding, wherein, scene characteristic object obtains by encoding to the scene characteristic preset in advance.Certainly, adopt different matching ways to have different coded systems, even can not encode, the embodiment of the present invention is not construed as limiting this.
In embodiments of the present invention, to the scene characteristic coding preset in advance, can be that the scene characteristic of picture, speech text form is encoded, obtain the vector being convenient to contrast.Accordingly, encoding to video flowing, can be extract image, captions, voice etc. from video flowing, and these information codings are become corresponding vector.
In an execution mode of the embodiment of the present invention, above-mentioned steps S102, can mate feature object to be matched with scene characteristic object; If the similarity of feature object to be matched and scene characteristic object meets pre-conditioned, using scene characteristic corresponding for scene characteristic object as scene characteristic corresponding to video flowing.
In an execution mode of the embodiment of the present invention, in advance to the scene characteristic coding preset, can according to scene mode corresponding to scene characteristic preset, classify and the scene characteristic preset encoded.Such as, different coding methods is adopted for image, voice.
In an execution mode of the embodiment of the present invention, above-mentioned default scene characteristic can comprise: the first scene characteristic and/or the second scene characteristic, and wherein, the first scene characteristic is general scene characteristic, and the second scene characteristic is the special scene characteristic of video flowing.Above-mentioned general scene characteristic can be the scene characteristic be all suitable for all videos, also can be the scene characteristic be suitable for a class video.Above-mentioned special scene characteristic can be the scene characteristic arranged for single video, also can be the scene characteristic arranged for some video.
In embodiments of the present invention, above-mentioned recommendation information corresponding to video flowing that present can be the link showing recommendation information on screen, also can be directly show recommendation information.
In an execution mode of the embodiment of the present invention, the presentative time of recommendation information can be set, present recommendation information corresponding to video flowing in the time of presetting.
In an execution mode of the embodiment of the present invention, video flowing can be the video flowing to be played of buffer memory, when playing this video flowing, can present the recommendation information that this video flowing is corresponding.Such as, scene matching is carried out to the video flowing to be played of buffer memory, obtains the recommendation information that video flowing is corresponding, when this video of private room, present this recommendation information.Such as, be the video flowing of buffer memory, recognize wherein section sometime and occurred conference scenario, then, while the video playing this time period, the recommendation information relevant to meeting can be presented, such as office equipment advertisement, meeting hotel information etc.
In an execution mode of the embodiment of the present invention, recommendation information can also being provided with recommendation identification code, recommending identification code for distinguishing recommendation information; The corresponding relation of scene characteristic and recommendation information is scene characteristic and the corresponding relation recommending identification code.
Fig. 2 is the structured flowchart of the information recommending apparatus based on scene Recognition according to the embodiment of the present invention, and as shown in Figure 2, this device mainly comprises: matching module 10, acquisition module 20 and present module 30.Matching module 10, for being mated with the scene characteristic preset by video flowing, obtains the scene characteristic that video flowing is corresponding; Acquisition module 20, for the corresponding relation according to scene characteristic and recommendation information, obtains the recommendation information that video flowing is corresponding.
In an execution mode of the embodiment of the present invention, matching module 10, comprising: coding unit, for encoding to video flowing, obtains feature object to be matched; Matching unit, for being mated with scene characteristic object by feature object to be matched, obtains the scene characteristic that video flowing is corresponding, and wherein scene characteristic object obtains by encoding to the scene characteristic preset in advance.
In an execution mode of the embodiment of the present invention, above-mentioned coding unit, also for according to scene mode corresponding to scene characteristic preset, classifies and to encode to the scene characteristic preset, obtain scene characteristic object.
In an execution mode of the embodiment of the present invention, the scene mode of scene characteristic preset comprise following one of at least: video scene, voice scene, captions scene, story of a play or opera scene.
In an execution mode of the embodiment of the present invention, the form of above-mentioned default scene characteristic comprise following one of at least: picture, text, voice.
In an execution mode of the embodiment of the present invention, the scene characteristic preset, comprising: the first scene characteristic and/or the second scene characteristic, wherein, the first scene characteristic is general scene characteristic, and the second scene characteristic is the special scene characteristic of video flowing.
In embodiments of the present invention, can also comprise: present module, for presenting recommendation information corresponding to video flowing.
In an execution mode of the embodiment of the present invention, present module, for presenting recommendation information corresponding to described video flowing in the time of presetting.
In an execution mode of the embodiment of the present invention, video flowing is the video flowing to be played of buffer memory, presents module 30, for when displaying video stream, presents the recommendation information that video flowing is corresponding.
In embodiments of the present invention, recommendation information can be provided with recommendation identification code, recommends identification code for distinguishing recommendation information; The corresponding relation of scene characteristic and recommendation information is scene characteristic and the corresponding relation recommending identification code.
The said method of the embodiment of the present invention and device, can realize within one device, also can be realized alternately by multiple equipment.The modules of said apparatus, can be arranged in an equipment, also can distribute on different devices.The embodiment of the present invention does not limit this.
Fig. 3 is the flowchart 2 of the information recommendation method based on scene Recognition according to the embodiment of the present invention, and as shown in Figure 3, the method comprising the steps of S302 is to step S306.
Step S302, video flowing mates with the scene characteristic preset by the first equipment, obtains the scene characteristic that this video flowing is corresponding.
Step S304, the scene characteristic that the first equipment is corresponding according to video flowing, obtains recommendation information corresponding to video flowing from the second equipment.
Step S306, the first equipment presents recommendation information corresponding to above-mentioned video flowing.
In embodiments of the present invention, the first above-mentioned equipment can be the equipment such as Set Top Box, mobile terminal.In above-mentioned steps S302, video flowing can mate with the scene characteristic preset in this locality by the first equipment.In addition, first equipment also can perform above-mentioned steps S302 by the second equipment, first equipment can be encoded to video flowing, obtain feature object to be matched, send feature object to be matched to the second equipment, and second equipment that receives mates scene characteristic corresponding to the video flowing that obtains according to feature object to be matched.By realizing coupling on the second device, can reduce the performance requirement to the first equipment, the first equipment does not need to do complicated process.
In an execution mode of the embodiment of the present invention, the first equipment carries out coupling and can comprise in this locality: the first equipment is encoded to video flowing, obtains feature object to be matched; Feature object to be matched mates with scene characteristic object by the first equipment, obtains the scene characteristic that video flowing is corresponding, and wherein, scene characteristic object obtains by encoding to the scene characteristic preset in advance.Coding with reference to the aforementioned description of the embodiment of the present invention, can not repeat them here.
Before above-mentioned steps S302, the first equipment can obtain from the second equipment the scene characteristic preset, wherein, the scene characteristic preset comprises the first scene characteristic and/or the second scene characteristic, wherein, the first scene characteristic is general scene characteristic, and the second scene characteristic is the special scene characteristic of video flowing.
In order to obtain the scene characteristic preset from the second equipment, the first equipment can send a request message to the second equipment, wherein carries the first update time of the scene characteristic prestored in the first equipment in this request message; First equipment receives the second equipment, when first upgrades the second update time of the scene characteristic be not later than on the second equipment, and the scene characteristic preset of transmission.By carrying update time, the information interaction between the first equipment and the second equipment can be reduced, having more under news in scene characteristic, sending the scene characteristic upgraded.
In a preferred implementation of the embodiment of the present invention, the first equipment is previously stored with above-mentioned first scene characteristic, and the first equipment can obtain the second scene characteristic from the second equipment.The first above-mentioned scene can be that the first device request sends from other equipment, also can be other equipment active arrangement to the first equipment, other equipment can comprise above-mentioned second equipment.
In an execution mode of the embodiment of the present invention, in above-mentioned steps S304, first equipment can send scene characteristic corresponding to video flowing to the second equipment, and the recommendation information that the video flowing receiving the second equipment transmission is corresponding, wherein, the second equipment is used for obtaining recommendation information corresponding to described video flowing according to scene characteristic and the corresponding relation of recommendation information.
In another execution mode of the embodiment of the present invention, in above-mentioned steps S304, first equipment can according to the corresponding relation of the recommendation identification code of scene characteristic and recommendation information, determine the recommendation identification code corresponding to the scene characteristic that video flowing is corresponding, and the recommendation identification code determined is sent to the second equipment, the recommendation information that the video flowing that second equipment that receives sends is corresponding, wherein, second equipment is used for obtaining recommendation information corresponding to video flowing according to recommendation identification code with the corresponding relation of recommendation information, wherein, recommend identification code for identifying recommendation information.
In embodiments of the present invention, above-mentioned steps S306, the first equipment can present recommendation information according to the time of presetting.Above-mentioned video flowing can be the video to be played of buffer memory, can present recommendation information when playing this video flowing.In addition, can be present recommendation information on the first device, also can be that the first equipment presents recommendation information by other equipment.Such as, be the situation of Set Top Box for the first equipment, the first equipment can present recommendation information on the television terminal of Set Top Box.
Fig. 4 is the structured flowchart one of the first equipment according to the embodiment of the present invention, and as shown in Figure 4, the first equipment mainly comprises: matching module 402, first acquisition module 404 and present module 406.Wherein, matching module 402, for being mated with the scene characteristic preset by video flowing, obtains the scene characteristic that video flowing is corresponding; First acquisition module 404, is connected with matching module 402, for the scene characteristic corresponding according to video flowing, obtains recommendation information corresponding to video flowing from the second equipment; And, present module 406, be connected with the first acquisition module 404, for presenting recommendation information corresponding to video flowing.
In an execution mode of the embodiment of the present invention, matching module 402, for mating video flowing with the scene characteristic preset on the first device; And/or matching module 402 can comprise: coding unit, for encoding to video flowing, obtain feature object to be matched; Transmitting element, for sending feature object to be matched to the second equipment; Receiving element, mates scene characteristic corresponding to the video flowing that obtains for receiving the second equipment according to feature object to be matched.
In an execution mode of the embodiment of the present invention, above-mentioned first equipment can also comprise: the second acquisition module, for obtaining the scene characteristic preset from the second equipment, wherein, the scene characteristic preset comprises the first scene characteristic and/or the second scene characteristic, wherein, the first scene characteristic is general scene characteristic, and the second scene characteristic is the special scene characteristic of above-mentioned video flowing.
In an execution mode of the embodiment of the present invention, the second acquisition module, comprising: transmitting element, for sending a request message to the second equipment, carries the first update time of the scene characteristic prestored in the first equipment in wherein said request message; Receiving element, for receiving the second equipment, when being not later than the second update time of the scene characteristic on the second equipment the first update time, the scene characteristic preset of transmission.
In embodiments of the present invention, the first equipment can prestore the first scene characteristic, the second acquisition module, for obtaining the second scene characteristic from the second equipment.
Above-mentioned first acquisition module 404 can comprise: the first acquiring unit, for sending scene characteristic corresponding to video flowing to the second equipment, and the recommendation information that the video flowing receiving the second equipment transmission is corresponding, wherein, the second equipment is used for obtaining recommendation information corresponding to described video flowing according to scene characteristic and the corresponding relation of recommendation information.Or, second acquisition unit, for the corresponding relation of the recommendation identification code according to scene characteristic and recommendation information, determine the recommendation identification code corresponding to the scene characteristic that video flowing is corresponding, and send the recommendation identification code determined to the second equipment, the recommendation information that the video flowing that second equipment that receives sends is corresponding, wherein, second equipment is used for obtaining recommendation information corresponding to video flowing according to recommendation identification code with the corresponding relation of recommendation information, wherein, recommends identification code for identifying recommendation information.
Fig. 5 is the structured flowchart two of the first equipment according to the embodiment of the present invention, and as shown in Figure 2, this first equipment comprises: communication interface 502, for the second equipment and at least one the 3rd devices communicating; At least one processor 504, for being mated with the scene characteristic preset by video flowing, obtains the scene characteristic that video flowing is corresponding; The scene characteristic corresponding according to video flowing, obtains recommendation information corresponding to described video flowing from the second equipment; And, present the recommendation information that video flowing is corresponding.
At least one above-mentioned processor 504 can also perform the said method of the embodiment of the present invention, does not repeat them here.
Fig. 6 is the flow chart 3 of the information recommendation method based on scene Recognition according to the embodiment of the present invention, and as shown in Figure 6, the method comprising the steps of S602 is to step S604.
Step S602, the first request of the second device responds first equipment, the video flowing of being asked by the first equipment mates with the scene characteristic preset, and obtains the scene characteristic that video flowing is corresponding.
Step S604, the second equipment according to the corresponding scene characteristic of video flowing, according to the corresponding relation of scene characteristic with recommendation information, to the recommendation information that the first equipment transmission video flowing is corresponding.
In an execution mode of the embodiment of the present invention, in above-mentioned steps S602, carry the feature object to be matched of video flowing in the first request, wherein, feature object to be matched carries out coding by the first equipment to video flowing and obtains.
In above-mentioned steps S604, the second equipment according to the corresponding relation of described scene characteristic and recommendation information, can send recommendation information corresponding to video flowing to the first equipment; Or the second equipment according to the corresponding relation of scene characteristic and recommendation information, can obtain the recommendation information that video flowing is corresponding; Second equipment sends the recommendation identification code of the recommendation information obtained to the first equipment, wherein, recommend identification code for distinguishing recommendation information.
In an execution mode of the embodiment of the present invention, said method can also comprise: the second request of the second device responds first equipment, according to the recommendation identification code of carrying in the second request, sends recommendation information corresponding to the identification code that carries to the first equipment.In embodiments of the present invention, the first equipment when receiving multiple recommendation identification code, can obtain recommendation information to the second device request, also can receive one and recommend identification code just to obtain corresponding recommendation information.
In an execution mode of the embodiment of the present invention, said method can also comprise: the 3rd request of the second device responds first equipment, according to the second update time of the scene characteristic on first update time of carrying in the 3rd request and the second equipment, scene characteristic is sent to the first equipment, wherein, the first update time was the update time of the scene characteristic that the first equipment stores; Wherein, described first update time, the second equipment sent scene characteristic to the first equipment early than the second update time.
In embodiments of the present invention, above-mentioned default scene characteristic can comprise: the first scene characteristic and/or the second scene characteristic, and wherein, the first scene characteristic is general scene characteristic, and the second scene characteristic is the special scene characteristic of video flowing.About the first scene characteristic and the second scene characteristic see the aforementioned description of the embodiment of the present invention, do not repeat them here.
Preferably, the 3rd message is for asking the second scene characteristic, and wherein, the first equipment is previously stored with the first scene characteristic.
Fig. 7 is the structured flowchart one of the second equipment according to the embodiment of the present invention, comprising: matching module 702 and the first sending module 704.Wherein, matching module 702, for responding the first request of the first equipment, the video flowing of being asked by the first equipment mates with the scene characteristic preset, and obtains the scene characteristic that video flowing is corresponding; First sending module 704, is connected with matching module 702, for according to the corresponding scene characteristic of video flowing, according to the corresponding relation of scene characteristic with recommendation information, to the recommendation information that the first equipment transmission video flowing is corresponding.
In embodiments of the present invention, carry the feature object to be matched of video flowing in the first request, wherein, feature object to be matched carries out coding by the first equipment to video flowing and obtains.
In an execution mode of the embodiment of the present invention, the first sending module 704 can comprise: the first transmitting element, for the corresponding relation according to scene characteristic and recommendation information, sends recommendation information corresponding to video flowing to the first equipment; Or the second transmitting element, for the corresponding relation according to scene characteristic and recommendation information, obtains the recommendation information that video flowing is corresponding; Sending the recommendation identification code of the recommendation information obtained to the first equipment, wherein, recommending identification code for distinguishing recommendation information.
In an execution mode of the embodiment of the present invention, above-mentioned second equipment can also comprise: the second sending module, for the second request responded, according to the recommendation identification code of carrying in the second request, send recommendation information corresponding to the identification code that carries to the first equipment.
In an execution mode of the embodiment of the present invention, above-mentioned second equipment can also comprise: the 3rd sending module, for responding the 3rd request of the first equipment, according to the second update time of the scene characteristic on first update time of carrying in the 3rd request and the second equipment, scene characteristic is sent to the first equipment, wherein, the first update time was the update time of the scene characteristic that described first equipment stores; Wherein, if the first update time is early than the second update time, the 3rd sending module sends scene characteristic to the first equipment.
In embodiments of the present invention, the scene characteristic preset comprises: the first scene characteristic and/or the second scene characteristic, wherein, the first scene characteristic is general scene characteristic, and the second scene characteristic is the special scene characteristic of described video flowing.For the first scene characteristic and the second scene characteristic see the aforementioned description of the embodiment of the present invention, do not repeat them here.
Preferably, the 3rd message is for asking the second scene characteristic, and wherein, the first equipment can prestore the first scene characteristic.
Fig. 8 is the structured flowchart two of the second equipment according to the embodiment of the present invention, and as shown in Figure 8, the second equipment can comprise: communication interface 802, is connected with at least one processor 804, for the first equipment and at least one the 3rd devices communicating; At least one processor 804, for responding the first request of the first equipment, the video flowing of being asked by the first equipment mates with the scene characteristic preset, and obtains the scene characteristic that video flowing is corresponding; According to the corresponding scene characteristic of video flowing, according to the corresponding relation of scene characteristic and recommendation information, send recommendation information corresponding to described video flowing to described first equipment.
At least one processor 804 can also perform the said method of the embodiment of the present invention, does not repeat them here.
By the embodiment of the present invention, video flowing is mated with the scene characteristic preset, obtains the scene characteristic that video flowing is corresponding; According to the corresponding relation of scene characteristic and recommendation information, obtain the recommendation information that video flowing is corresponding; And present recommendation information corresponding to video flowing, can recommendation information more accurately based on video scene.
Below the preferred implementation of the embodiment of the present invention is described.
Fig. 9 is according to the embodiment of the present invention preferably based on the schematic diagram of the information recommendation system of scene Recognition, as shown in Figure 9.This system mainly comprises: recommendation server (being equivalent to the second above-mentioned equipment) 1, be responsible for preset scene mode and scene characteristic information (also referred to as scene characteristic in above-described embodiment), and provide concrete business recommended form according to recommendation identification code; Set Top Box (being equivalent to the first above-mentioned equipment) 2, be responsible for generating and storage scenarios characteristic information, the buffer memory of code stream and identification, characteristic matching and recommendation identification code generation; IPTV/OTT system 3, mainly provides basic video playback capability; Third party system 4, mainly provides specifically presenting of various recommendation business.
Said system mainly comprises following reciprocal process: scene issues, and mainly recommendation server 1 is according to preset scene mode, issues scene characteristic; Scene generates, and Set Top Box 2 pairs of scene characteristic are encoded, and the scene characteristic object of generation and recommendation identification code are stored into scene characteristic storehouse; Scene Recognition, Set Top Box 2 carries out code stream buffer memory when playing the video from IPTV/OTT system 3, and carry out pre-parsed to buffer memory code stream, analysis result carries out Intelligent Matching, if the match is successful, then exports recommended characteristics code; Business recommended, Set Top Box 2 initiates request according to recommendation identification code to recommendation server, and shows the recommendation page according to the recommendation information returned, and then is redirected to Third party system.
Such as, when user selects to watch certain video, effective Intelligent Recognition is carried out to the scene of the video content in IPTV system, and then carry out interaction recommendation according to information such as the image comprised in video content, dialogue, the story of a play or opera, performers, the specific aim of recommendation can well be solved, relevance problem, promotes user interactive, really reaches to manipulate certain content according to user and just can automatically carry out the concrete business such as recommended advertisements, shopping.
Figure 10 is according to the embodiment of the present invention preferably based on the structured flowchart of the information recommendation system of scene Recognition, and as shown in Figure 10, this system comprises Set Top Box 2, recommendation server 1, IPTV/OTT system 3, Third party system 4.Set Top Box 2 comprises: scenario generating module 210, scene characteristic storehouse 220, code stream identification module 230, characteristic matching module 240 and business recommended module 250.
(1) in recommendation server, scene characteristic information is safeguarded, as video scene, voice scene, captions scene, story of a play or opera scene etc., wherein, video scene mainly needs the pictorial information such as performer, clothes, article, food mated in typing video; Keyword in the dialogue that voice scene mainly needs in typing video to mate, aside; The captions keyword that captions scene mainly needs in typing video to mate, story of a play or opera scene mainly need the preset story of a play or opera time point mated in typing video;
(2) in recommendation server, one can be bound to each scene characteristic information and recommend identification code, set up the incidence relation of scene characteristic and recommendation identification code; Safeguard the relation of recommending identification code and recommendation information, for the identification of recommendation information simultaneously;
(3) scenario generating module in Set Top Box accepts the scene characteristic information (comprise and recommend identification code) from recommendation server, according to different scene modes, as video scene, voice scene, captions scene, story of a play or opera scene etc., carry out encoding and generate the scene characteristic object of certain semantic, and be saved in scene characteristic storehouse;
(4) the code stream identification module in Set Top Box is responsible for the code stream in pre-parsed buffer memory, generates feature object to be matched;
(5) feature object to be matched and scene characteristic storehouse are carried out computing and are mated by the characteristic matching module in Set Top Box, if feature to be matched comprises certain scene characteristic in scene characteristic storehouse, then obtain this scene characteristic correspondence and recommend identification code;
(6) the business recommended module in Set Top Box is after getting recommendation identification code, be responsible for recommendation server acquisition request recommendation information, and recommendation information is showed user by predetermined form, user can by showing that recommendation information jumps to Third party system, obtain more detailed business information, the whole process that finishing service is recommended.
Based on realizing principle shown in Fig. 1, realizing the business recommended method based on scene intelligent identification in the embodiment of the present invention, comprising following step:
Steps A: recommendation server carries out scene characteristic maintenance and issues.
Step B: Set Top Box receives the scene characteristic from recommendation server, generating scene feature.
Step C: Set Top Box receives the video flowing from IPTV/OTT system, and carries out scene Recognition coupling.
Step D: Set Top Box according to matching result, generating recommendations information.
Figure 11 is the flow chart issued according to the scene characteristic of the embodiment of the present invention, performs in above-mentioned steps A, and implementation step is as follows:
Step S1102: typing scene characteristic information in recommendation server, includes but not limited to video scene, voice scene, captions scene, story of a play or opera scene etc.; Scene characteristic information can be bound with concrete video, also can be full video adaptation.
Step S1104: the business recommended information of typing in recommendation server, and generate a unique recommendation identification code for each business recommended information.
Step S1106: bind scene characteristic information and business recommended information in recommendation server, binding relationship is set up by recommending identification code, can realize two-way consulting.
Step S1108: Set Top Box, before viewing video, obtains the request of general scene characteristic information to recommendation server, and carries user profile and issue timestamp; The behavior according to the actual requirements, can advance to when set-top-box opening starts and obtains, to reduce the frequent scene characteristic information obtaining repetition before viewing video.
Step S1110: recommendation server detects user validation, if detect by and up-to-date timestamp on server with issue timestamp field and contrast and have renewal, then issue video feature information and recommend identification code to Set Top Box, the agreement issued can based on but be not limited to http protocol.
Step S1112: Set Top Box, before displaying video, obtains the request of concrete video scene characteristic information, and carries user profile, context number and issue timestamp to recommendation server.
Step S1114: recommendation server detects user validation, if detect by and up-to-date timestamp on server with issue timestamp field and contrast and have renewal, then issue concrete video scape characteristic information and recommend identification code to Set Top Box, the agreement issued can based on but be not limited to http protocol.
Figure 12 is the flow chart generated according to the scene characteristic of the embodiment of the present invention, and perform in above-mentioned steps B, implementation step is as follows:
Step S1202: Set Top Box receives the scene characteristic information from recommendation server.
Step S1204: the scenario generating module of Set Top Box is to scene characteristic information, and according to scene mode, classification is encoded, and generates the scene characteristic object of certain semantic.
Step S1206: the scenario generating module of Set Top Box is set up scene characteristic object and recommended the incidence relation of identification code.
Step S1208: Set Top Box is unifiedly stored to scene characteristic storehouse by the scene characteristic object of generation and with recommending the incidence relation of identification code, and storage issues timestamp.
Figure 13 is the flow chart mated according to the scene characteristic of the embodiment of the present invention, and perform in above-mentioned steps C, implementation step is as follows:
Step S1302: Set Top Box plays the video code flow from IPTV/OTT system, and carries out buffer memory to code stream.
Step S1304: the code stream identification module of Set Top Box identifies buffer memory code stream, can identify for every two field picture of video, one section of voice, captions, reproduction time, and carry out the feature object to be matched being formed and meet certain semantic of encoding, and pass to characteristic matching module.Wherein voice and captions mainly form word, and reproduction time is absolute time and relative time mainly, and absolute time format adopts date Hour Minute Second, and relative time form adopts Hour Minute Second.
Step S1306: feature object to be matched and scene characteristic storehouse are carried out computing matching operation by the characteristic matching template in Set Top Box.
Step S1308: if feature to be matched comprises certain scene characteristic in scene characteristic storehouse, as in the feature that comprises in image and scene characteristic storehouse, picture feature object ratio reaches threshold values, voice in code stream and captions contain the corresponding word keyword in scene characteristic storehouse, preset story of a play or opera time point arrives, then the match is successful, then walk step S1305, if it fails to match, direct discard processing.
Step S1310: characteristic matching template obtains this scene characteristic correspondence and recommends identification code from scene characteristic storehouse.
Step S1312: meanwhile, the reproduction time of video code flow under characteristic matching template record, and the recommendation triggered time is set to business recommended module, prepare trigger business recommended flowsheet.
Figure 14 is the flow chart of the information recommendation according to the embodiment of the present invention, performs in above-mentioned steps D, and implementation step is as follows:
Step S1402: whether the business recommended module in Set Top Box judges to recommend the triggered time to arrive; If arrived, then enter step S1404.
Step S1404: the business recommended module assembled request message in Set Top Box, initiates request to recommendation server, carries user profile and recommend identification code in request message.
Step S1406: after recommendation server receives set-top box requests, detects user validation, passes through if detected, then according to recommendation identification code, return concrete recommendation information, generally comprise showing interface information and URL thereof.
Step S1408: after the business recommended module in Set Top Box receives recommendation information, resolve, and according to the assembling of predetermined template style, show user.
Step S1410: user, after watching the recommendation page, can, according to the hobby of oneself, select whether to carry out the behaviors such as shopping from recommendation page jump to Third party system.
For the ease of better understanding the scheme and principle that this embodiment of the present invention provides, below by several specific embodiment, the present invention is elaborated.
Embodiment 1
Based on the local scene Recognition of Set Top Box, the scenario generating module of the Set Top Box in described schematic diagram, scene characteristic storehouse, code stream identification module, characteristic matching storehouse, business recommended module are all built in Set Top Box, to carry out scene Recognition coupling, as shown in figure 15, its step comprises:
Step S1502: user clicks video, Set Top Box issues scene characteristic to recommendation server request.
Step S1504: Set Top Box carries out scene characteristic coding, and be stored into scene characteristic storehouse.
Video in step S1506: when user watches video, set-top box requests IPTV/OTT system, and receiver, video code stream.
Step S1508: Set Top Box carries out buffer memory to code stream, and recognition coding is carried out to buffer memory code stream, generate discernible feature object to be matched.
Step S1510: feature object to be matched and characteristic matching storehouse are carried out identification and mated by Set Top Box, obtains and recommends identification code.
Step S1512: Set Top Box is carried and recommended identification code to obtain recommendation information to recommendation server.
Step S1514: the recommendation information that set-top box parses recommendation server returns, and present to user.
Embodiment 2
Based on the scene Recognition in high in the clouds, in described schematic diagram, the scenario generating module of Set Top Box, scene characteristic storehouse, characteristic matching module move on to recommendation server, recommendation server is as the scene Recognition process in high in the clouds, and code stream identification module and business recommended module continue to be placed on Set Top Box feature reports and recommendation request, as shown in figure 16, its step comprises:
Step S1602: recommendation server carries out the coding of scene characteristic, and be stored into scene characteristic storehouse.
Video in step S1604: when user watches video, set-top box requests IPTV/OTT system, and receiver, video code stream.
Step S1606: Set Top Box carries out buffer memory to code stream, and recognition coding is carried out to buffer memory code stream, generate discernible feature object to be matched.
Step S1608: feature object to be matched sends to recommendation server to carry out high in the clouds coupling by Set Top Box.
Step S1610: feature object to be matched and characteristic matching storehouse are carried out identification and mated by recommendation server, obtains and recommends identification code.
Step S1612: recommendation server returns recommends identification code to Set Top Box.
Step S1614: Set Top Box is carried and recommended identification code to obtain recommendation information to recommendation server.
Step S1616: the recommendation information that set-top box parses recommendation server returns, and present to user.
Embodiment 3
Based on the scene Recognition of mobile terminal (as mobile phone, Pad etc.), by module corresponding in Set Top Box, all can be transplanted to mobile terminal, realize the scene Recognition of mobile terminal and business recommended.Mobile terminal accesses mainly through wireless network, accesses for Wifi mode, and the flow process of specific embodiment can be carried out with reference to embodiment 1, does scene matching at mobile terminal; When accessing for 3G/4G pattern, more needs are considered to reduce network interaction and data traffic, therefore the high in the clouds tupe of in conjunction with the embodiments 2 is needed, server side identifies for video-frequency band beyond the clouds, all recommendation identification codes of this video-frequency band are returned after identifying coupling, as shown in figure 17, its step comprises:
Step S1702: recommendation server carries out the coding of scene characteristic, and be stored into scene characteristic storehouse.
Video in step S1704: when user watches video, mobile terminal request IPTV/OTT system, and receiver, video code stream.
Step S1706: mobile terminal initiates characteristic matching request to recommendation server, and this request is for the video code flow time period.
Step S1708: recommendation server, to the video code flow time period of request, carries out match cognization beyond the clouds, and generates multiple recommendation identification code.
Step S1710: recommendation server returns multiple recommendation identification code to mobile terminal.
Step S1712: each recommendation identification code of mobile terminal records and recommendation triggered time thereof.
Step S1714: mobile terminal, after the recommendation triggered time arrives, carries and recommends identification code to obtain recommendation information to recommendation server.
Step S1716: mobile terminal resolves the recommendation information that recommendation server returns, and presents to user.
Step S1718: mobile terminal, according to video-see progress, starts the characteristic matching request of next section of video code flow, repeats step S1706.
Embodiment 4
Based on the scene Recognition of video pre-filtering pattern, this pattern all carries out match cognization in advance beyond the clouds mainly for video, major advantage is that coupling is quick, not high to demanding terminal, there is good versatility, because video is when IPTV/OTT system is issued, whole various scene matching of preliminary treatment, and generate the recommendation identification code of video and recommend the triggered time, but owing to being preliminary treatment, the personal characteristics coupling taking into account user cannot be paid close attention to.As shown in figure 18, its step comprises:
Step S1802: recommendation server carries out batch preliminary treatment for the video in IPTV/OTT system, mates with scene characteristic storehouse, identifies one by one video.
Step S1804: the recommendation identification code that recommendation server generates according to the result of match cognization and recommend the triggered time, and correspondingly with video to store.
Video in step S1806: when user watches video, Set Top Box mobile terminal request IPTV/OTT system, and receiver, video code stream.
Step S1808: Set Top Box/mobile terminal initiates characteristic matching request to recommendation server.
Step S1810: the preliminary treatment matching result that recommendation server inquiry stores, if hit, then returns results.
Step S1812: recommendation server returns the whole recommendation identification code of this video to Set Top Box/mobile terminal.
Step S1814: each recommendation identification code of Set Top Box/mobile terminal records and recommendation triggered time thereof.
Step S1816: Set Top Box/mobile terminal, after the recommendation triggered time arrives, carries and recommends identification code to obtain recommendation information to recommendation server.
Step S1818: mobile terminal resolves the recommendation information that recommendation server returns, and presents to user.
From above description, can find out, present invention achieves following technique effect well to solve in video existing information and business recommended information and associate and interaction, and multiple video sharing service recommendation information, allow user can viewing video process in, obtain relevant recommendation information along with the change of video scene, improve the interactive of user, also enhance business recommended specific aim and versatility; In IPTV/OTT system, for based on video content Intelligent Recognition and business recommended field, there is general practical application meaning.
Obviously, those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on network that multiple calculation element forms, alternatively, they can realize with the executable program code of calculation element, thus, they can be stored and be performed by calculation element in the storage device, and in some cases, step shown or described by can performing with the order be different from herein, or they are made into each integrated circuit modules respectively, or the multiple module in them or step are made into single integrated circuit module to realize.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (14)
1. based on an information recommendation method for scene Recognition, it is characterized in that, comprising:
Video flowing is mated with the scene characteristic preset, obtains the scene characteristic that described video flowing is corresponding;
According to the corresponding relation of scene characteristic and recommendation information, obtain the recommendation information that described video flowing is corresponding.
2. method according to claim 1, is characterized in that, is mated by video flowing, comprising with the scene characteristic preset:
Described video flowing is encoded, obtains feature object to be matched;
Mated with scene characteristic object by described feature object to be matched, obtain the scene characteristic that described video flowing is corresponding, wherein, described scene characteristic object obtains by encoding to described default scene characteristic in advance.
3. method according to claim 2, is characterized in that, is mated by described feature object to be matched, obtain the scene characteristic that described video flowing is corresponding, comprising with scene characteristic object:
Described feature object to be matched is mated with described scene characteristic object;
If the similarity of described feature object to be matched and described scene characteristic object meets pre-conditioned, using scene characteristic corresponding for described scene characteristic object as scene characteristic corresponding to described video flowing.
4. method according to claim 2, is characterized in that, in advance to described default scene characteristic coding, comprising:
According to the scene mode that described default scene characteristic is corresponding, classify and described default scene characteristic encoded.
5. the method according to claim 1 or 4, is characterized in that, the scene mode of described default scene characteristic comprise following one of at least: video scene, voice scene, captions scene, story of a play or opera scene.
6. method according to claim 1, is characterized in that, the form of described default scene characteristic comprise following one of at least: picture, text, voice.
7. method according to claim 1, is characterized in that, described default scene characteristic, comprise: the first scene characteristic and/or the second scene characteristic, wherein, described first scene characteristic is general scene characteristic, and described second scene characteristic is the special scene characteristic of described video flowing.
8. method according to claim 1, is characterized in that, also comprises: present the recommendation information that described video flowing is corresponding.
9. method according to claim 1, is characterized in that, described video flowing is the video flowing to be played of buffer memory, and the recommendation information presenting described video flowing corresponding comprises: when playing described video flowing, present the recommendation information that described video flowing is corresponding.
10. method according to claim 1, is characterized in that, described recommendation information is provided with recommendation identification code, and described recommendation identification code is for distinguishing recommendation information; The corresponding relation of described scene characteristic and recommendation information is scene characteristic and the corresponding relation recommending identification code.
11. 1 kinds based on the information recommending apparatus of scene Recognition, is characterized in that, comprising:
Matching module, for being mated with the scene characteristic preset by video flowing, obtains the scene characteristic that described video flowing is corresponding;
Acquisition module, for the corresponding relation according to scene characteristic and recommendation information, obtains the recommendation information that described video flowing is corresponding.
12. devices according to claim 11, is characterized in that, described matching module, comprising:
Coding unit, for encoding to described video flowing, obtains feature object to be matched;
Matching unit, for being mated with scene characteristic object by described feature object to be matched, obtains the scene characteristic that described video flowing is corresponding, and wherein, described scene characteristic object obtains by encoding to described default scene characteristic in advance.
13. devices according to claim 12, is characterized in that, described coding unit, also for according to scene mode corresponding to described default scene characteristic, classify and to encode to described default scene characteristic, obtain described scene characteristic object.
14. devices according to claim 11, is characterized in that, also comprise: present module, for presenting recommendation information corresponding to described video flowing.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410300737.5A CN105227973A (en) | 2014-06-27 | 2014-06-27 | Based on information recommendation method and the device of scene Recognition |
| PCT/CN2014/093401 WO2015196749A1 (en) | 2014-06-27 | 2014-12-09 | Scenario recognition-based information recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410300737.5A CN105227973A (en) | 2014-06-27 | 2014-06-27 | Based on information recommendation method and the device of scene Recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105227973A true CN105227973A (en) | 2016-01-06 |
Family
ID=54936658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410300737.5A Pending CN105227973A (en) | 2014-06-27 | 2014-06-27 | Based on information recommendation method and the device of scene Recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105227973A (en) |
| WO (1) | WO2015196749A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017128482A1 (en) * | 2016-01-28 | 2017-08-03 | 宇龙计算机通信科技(深圳)有限公司 | Video pre-reminding processing method and device, and terminal |
| CN109640189A (en) * | 2018-12-19 | 2019-04-16 | 聚好看科技股份有限公司 | Information display method and device |
| CN109670106A (en) * | 2018-12-06 | 2019-04-23 | 百度在线网络技术（北京）有限公司 | Things recommended method and device based on scene |
| CN110097102A (en) * | 2019-04-22 | 2019-08-06 | 上海车轮互联网服务有限公司 | Data configuration method and device suitable for different business scene |
| CN110149558A (en) * | 2018-08-02 | 2019-08-20 | 腾讯科技（深圳）有限公司 | A kind of video playing real-time recommendation method and system based on content recognition |
| CN111091099A (en) * | 2019-12-20 | 2020-05-01 | 京东方科技集团股份有限公司 | Scene recognition model construction method, scene recognition method and device |
| WO2023060759A1 (en) * | 2021-10-11 | 2023-04-20 | 深圳创维－Rgb电子有限公司 | Video pushing method, device, and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110827099B (en) * | 2018-08-07 | 2022-05-13 | 阿里巴巴（中国）有限公司 | Household commodity recommendation method, client and server |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070186243A1 (en) * | 2006-02-08 | 2007-08-09 | Sbc Knowledge Ventures, Lp | System and method of providing television program recommendations |
| CN101677376A (en) * | 2008-09-18 | 2010-03-24 | 三菱电机株式会社 | Program recommendation apparatus |
| CN103475910A (en) * | 2013-08-27 | 2013-12-25 | 四川长虹电器股份有限公司 | Set-top box (STB) program recommending method and system for smart television (TV) terminal |
| CN103501449A (en) * | 2013-10-08 | 2014-01-08 | 十分（北京）信息科技有限公司 | Method and device for recommending video source associated with television program |
| CN103544216A (en) * | 2013-09-23 | 2014-01-29 | Tcl集团股份有限公司 | Information recommendation method and system combining image content and keywords |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040139173A1 (en) * | 2002-12-11 | 2004-07-15 | Jeyhan Karaoguz | Media processing system automatically offering access to newly available media in a media exchange network |
| EP2332111B2 (en) * | 2008-08-06 | 2023-10-11 | Invidi Technologies Corporation | Third party data matching for targeted advertising |
| CN101668165A (en) * | 2008-09-05 | 2010-03-10 | 华为技术有限公司 | Method, device and system for realizing advertisement in IPTV |
| CN103763589A (en) * | 2014-01-10 | 2014-04-30 | 北京酷云互动科技有限公司 | Video advertisement extended information pushing method and device |
-
2014
- 2014-06-27 CN CN201410300737.5A patent/CN105227973A/en active Pending
- 2014-12-09 WO PCT/CN2014/093401 patent/WO2015196749A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070186243A1 (en) * | 2006-02-08 | 2007-08-09 | Sbc Knowledge Ventures, Lp | System and method of providing television program recommendations |
| CN101677376A (en) * | 2008-09-18 | 2010-03-24 | 三菱电机株式会社 | Program recommendation apparatus |
| CN103475910A (en) * | 2013-08-27 | 2013-12-25 | 四川长虹电器股份有限公司 | Set-top box (STB) program recommending method and system for smart television (TV) terminal |
| CN103544216A (en) * | 2013-09-23 | 2014-01-29 | Tcl集团股份有限公司 | Information recommendation method and system combining image content and keywords |
| CN103501449A (en) * | 2013-10-08 | 2014-01-08 | 十分（北京）信息科技有限公司 | Method and device for recommending video source associated with television program |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017128482A1 (en) * | 2016-01-28 | 2017-08-03 | 宇龙计算机通信科技(深圳)有限公司 | Video pre-reminding processing method and device, and terminal |
| CN110149558A (en) * | 2018-08-02 | 2019-08-20 | 腾讯科技（深圳）有限公司 | A kind of video playing real-time recommendation method and system based on content recognition |
| CN110149558B (en) * | 2018-08-02 | 2023-03-28 | 腾讯科技（深圳）有限公司 | Video playing real-time recommendation method and system based on content identification |
| CN109670106A (en) * | 2018-12-06 | 2019-04-23 | 百度在线网络技术（北京）有限公司 | Things recommended method and device based on scene |
| CN109640189A (en) * | 2018-12-19 | 2019-04-16 | 聚好看科技股份有限公司 | Information display method and device |
| CN110097102A (en) * | 2019-04-22 | 2019-08-06 | 上海车轮互联网服务有限公司 | Data configuration method and device suitable for different business scene |
| CN111091099A (en) * | 2019-12-20 | 2020-05-01 | 京东方科技集团股份有限公司 | Scene recognition model construction method, scene recognition method and device |
| WO2023060759A1 (en) * | 2021-10-11 | 2023-04-20 | 深圳创维－Rgb电子有限公司 | Video pushing method, device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2015196749A1 (en) | 2015-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105227973A (en) | Based on information recommendation method and the device of scene Recognition | |
| EP2406732B1 (en) | Bookmarking system | |
| KR101506823B1 (en) | Method for transceiving media files and device for transmitting/receiving using same | |
| CN103067776B (en) | Program push method, system and intelligent display device, cloud server | |
| CN101960445B (en) | Techniques to consume content and metadata | |
| US20030097301A1 (en) | Method for exchange information based on computer network | |
| KR20120119758A (en) | Apparatus for providing iptv broadcasting contents, user terminal and method for providing iptv broadcasting contents information | |
| CN101094400A (en) | Method of creation of multimedia contents for mobile terminals, computer program product for the implementation of such a method | |
| US20220167036A1 (en) | Live broadcast method and apparatus, and computer device and storage medium | |
| CN103026681A (en) | Video-based method, server and system for realizing value-added service | |
| CN101606171A (en) | The apparatus and method of access and first media data correlation combiner information | |
| CN103856607A (en) | Method and system for delivering video on mobile phone terminal to video play device for playing | |
| CN102006519A (en) | Method and system for realizing interaction between multi-media terminal and internet protocol (IP) set top box | |
| CN103533460A (en) | Method, device, terminal and system for sharing television service | |
| US20150304718A1 (en) | Method And Terminal For Sharing Program In Interactive Network Television System | |
| CN103024454B (en) | Method and system for transmitting interaction entry information to audiences in broadcasting and TV programs | |
| US20140366055A1 (en) | Terminal, a set information inputting method of an electronic apparatus, a computer readable information storage medium, and an electronic apparatus | |
| CN103428538A (en) | Method, device and system for interaction of interactive broadcast televisions | |
| CN104168517A (en) | Method and system for entering live channels | |
| CN103167327A (en) | Method, device and system of information interaction | |
| CN105049921A (en) | Data processing method and device | |
| JP2012244286A (en) | Information processing terminal, application-cooperative content management server and location resolution server | |
| EP2827602B1 (en) | Method, apparatus and communication system for program information exchange | |
| CN102572529B (en) | The methods, devices and systems that a kind of program resource is play | |
| CN104427350A (en) | Associated content processing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160106 |