CN113055732A - Advertisement delivery method, advertisement delivery server, client and advertisement delivery system - Google Patents
Advertisement delivery method, advertisement delivery server, client and advertisement delivery system Download PDFInfo
- Publication number
- CN113055732A CN113055732A CN202110295684.2A CN202110295684A CN113055732A CN 113055732 A CN113055732 A CN 113055732A CN 202110295684 A CN202110295684 A CN 202110295684A CN 113055732 A CN113055732 A CN 113055732A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- target
- video
- client
- protocol
- 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
- 238000002716 delivery method Methods 0.000 title description 6
- 238000009877 rendering Methods 0.000 claims abstract description 56
- 239000000463 material Substances 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000013473 artificial intelligence Methods 0.000 claims description 29
- 238000012216 screening Methods 0.000 claims description 14
- 238000012423 maintenance Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 2
- 238000006243 chemical reaction Methods 0.000 description 4
- 239000012634 fragment Substances 0.000 description 4
- 230000029058 respiratory gaseous exchange Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010027146 Melanoderma Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
- H04N21/4316—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations for displaying supplemental content in a region of the screen, e.g. an advertisement in a separate window
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Abstract
The embodiment of the invention provides an advertisement putting method, an advertisement putting server, a client and an advertisement putting system. The method comprises the following steps: the advertisement delivery server receives a label pulling request; the advertisement delivery server returns a scene label corresponding to the video identifier of the target video to the client; receiving an advertisement request by an advertisement delivery service end; the advertisement request is sent by the client in advance before the target occurrence moment; the advertisement delivery server returns an advertisement protocol matched with the scene label identification in the advertisement request to the client; the client is used for calculating coordinate points for exploring advertisement rendering according to the position and the size of a target object issued by the advertisement protocol, and displaying advertisement materials in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information. The relevance of the advertisement and the video content is increased, the advertisement is explored, the putting positions are flexible and diverse, and the effect that the advertisement moves along the path of the target object can be achieved.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to an advertisement delivery method, an advertisement delivery server, a client, and an advertisement delivery system.
Background
The in-frame advertisements (5S front advertisement, 15S rear advertisement, etc.) are video advertisements that are currently used. Taking 5S advertisement, it is a 5S advertisement displayed in a form of graphics, text or video before the video content is played.
The inventor finds that the existing in-frame advertisement is limited by single position and has low relevance with video content, so that the advertisement has low attraction and low conversion rate.
Disclosure of Invention
In view of this, embodiments of the present invention provide an advertisement delivery method, an advertisement delivery server, a client, and an advertisement delivery system, so as to improve the relevance between an advertisement and video content and diversify the delivery position of the advertisement.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the first aspect of the present application provides a method for launching exploration advertisements, based on an advertisement launching system, the advertisement launching system includes: the system comprises an advertisement delivery server and a client; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label; the method comprises the following steps:
the advertisement delivery server receives a label pulling request; the label pulling request is sent when the client opens the target video; the label pulling request carries the video identification of the target video;
the advertisement delivery server returns a scene label corresponding to the video identifier of the target video to the client; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
the advertisement delivery server receives an advertisement request; the advertisement request is sent by the client in advance before the target occurrence moment; the advertisement request comprises returned scene label identification;
the advertisement delivery server side returns an advertisement protocol matched with the scene label identification in the advertisement request to the client side; the returned advertising protocol includes at least: the target object is associated with an advertisement material for exploring the advertisement, the launching time information of launching sections of the advertisement material, the position and the size of the target object in each target launching frame in the launching sections, and the rendering mode of the exploring advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment;
and the client is used for calculating coordinate points for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
Optionally, the advertisement protocol further includes playing time information of the target delivery frame; wherein the playing time information includes: at least one of the number of target delivery frames and a time interval between adjacent target delivery frames; the playing time information is used for the client to determine the playing time of each target putting frame in the putting segment.
Optionally, the returning, by the advertisement delivery server, the advertisement protocol to the client includes:
if the number of the advertisement protocols matched with the scene label identification is multiple, screening out a final advertisement protocol from the multiple advertisement protocols according to a screening condition;
returning the screened final advertisement protocol;
the screening condition includes at least one of a placement priority and a directional territory.
Optionally, before receiving the tag pull request, the method further includes:
the advertisement delivery server side provides the target video for an artificial intelligence recognition system; the artificial intelligence recognition system is used for recognizing the target object in the target video and generating a corresponding scene label;
and the advertisement delivery server receives the scene label returned by the artificial intelligence identification system.
Optionally, before receiving the tag pulling request, after receiving the scene tag returned by the artificial intelligence recognition system, the method further includes:
the advertising service end creates a corresponding advertising protocol based on the scene tag.
Optionally, the method further includes:
after the film source of the target video is changed, the advertisement delivery server informs the artificial intelligence recognition system to acquire the target video at a new film source, re-recognizes the target object in the target video, generates a new scene label and returns;
and the advertisement putting service end creates a corresponding new advertisement protocol based on the new scene label.
In a second aspect, the present application provides another advertisement discovery and placement method, based on an advertisement placement system, the advertisement placement system including: the system comprises an advertisement delivery server and a client; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label; the method comprises the following steps:
the client sends a label pulling request to the advertisement putting server when opening the target video; the label pulling request carries the video identification of the target video; the advertisement request comprises returned scene label identification;
the client receives a scene label corresponding to the target video; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
the client sends an advertisement request to the advertisement delivery server in advance before the target occurrence moment;
the client receives an advertisement protocol returned by the advertisement delivery server; the returned advertisement protocol includes at least: the target object is associated with advertisement material for exploring the advertisement, the launching time information of launching sections of the advertisement material, the position and the size of the target object in each target launching frame in the launching sections, and the rendering mode of the exploring advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment;
and the client calculates coordinate points for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displays the advertisement material in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
A third aspect of the present application provides an advertisement delivery server, including:
a maintenance unit for maintaining the video identifier, the scene tag associated with the video identifier, and the advertisement protocol associated with the scene tag;
an advertisement delivery unit configured to:
receiving a tag pull request; the label pulling request is sent when the client opens the target video; the label pulling request carries the video identification of the target video;
returning a scene label corresponding to the video identifier of the target video to the client; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
receiving an advertisement request; the advertisement request is sent by the client in advance before the target occurrence moment; the advertisement request comprises returned scene label identification;
returning an advertisement protocol matched with the scene label identification in the advertisement request to the client; the returned advertising protocol includes at least: exploring an advertisement material of an advertisement, launching time information of launching sections of the advertisement material, a position and a size of the target object in each target launching frame in the launching sections, and exploring a rendering mode of the advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment; and the client is used for calculating coordinate points for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
In the aspect of returning an advertisement agreement to the client, the advertisement delivery unit is specifically configured to:
if the number of the advertisement protocols matched with the scene label identification is multiple, screening out a final advertisement protocol from the multiple advertisement protocols according to screening conditions;
returning the screened final advertisement protocol;
the screening condition includes at least one of a placement priority and a directional territory.
Prior to receiving a tag pull request, the maintenance unit is further to:
providing a target video to an artificial intelligence recognition system; identifying a target object in a target video by an artificial intelligence identification system to generate a corresponding scene label;
and receiving the scene label returned by the artificial intelligence recognition system.
Before receiving the tag pulling request and after receiving the scene tag returned by the artificial intelligence recognition system, the maintenance unit is further configured to:
and creating a corresponding advertising protocol based on the scene label.
After the source of the target video is changed, the maintenance unit is further configured to:
informing an artificial intelligence recognition system to obtain a target video at a new film source, re-recognizing a target object in the target video, generating a new scene label and returning;
a corresponding new advertising protocol is created based on the new scene tag.
A fourth aspect of the present application provides a client, comprising:
a pulling unit for:
sending a label pulling request to the advertisement putting server side when a target video is opened; the label pulling request carries the video identification of the target video; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label;
receiving a scene label corresponding to the video identifier of the target video phase; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
sending an advertisement request to the advertisement delivery service terminal in advance before the target occurrence moment;
receiving an advertisement protocol returned by the advertisement delivery server; the returned advertisement protocol includes at least: exploring an advertisement material of an advertisement, launching time information of launching sections of the advertisement material, a position and a size of the target object in each target launching frame in the launching sections, and exploring a rendering mode of the advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment;
an exploration advertisement rendering unit to:
and calculating a coordinate point for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate point, the rendering mode and the delivery time information.
The advertisement protocol may further include play time information of the target delivery frame; wherein, the playing time information comprises: at least one of a number of targeted delivery frames and a time interval between adjacent targeted delivery frames.
The corresponding exploration advertisement rendering unit is specifically configured to:
determining each playing time of each target putting frame in the putting segment according to the putting time information and the playing time information;
and displaying the advertisement material in the currently displayed image frame based on the calculated coordinate point and the rendering mode at the determined playing time.
A fifth aspect of the present application provides an advertisement delivery system, including the advertisement delivery server provided in the third aspect of the present application and the client provided in the fourth aspect of the present application.
Therefore, in the embodiment of the invention, the exploration advertisement associated with the target object is put in the segment of the video where the target object appears, so that the relevance of the advertisement and the video content is increased. And the position of the target object in the video advertisement is determined according to the position of the target object in the video advertisement, and the video advertisement is not limited to be played before the head of the video or at the tail of the video.
Drawings
Fig. 1 is a schematic structural diagram of an advertisement delivery system according to an embodiment of the present invention;
fig. 2 is a schematic view of a scene in which a target object appears in an image frame of a video according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a preliminary preparation task for exploring advertisement placement according to an embodiment of the present invention;
FIGS. 4a and 4b are schematic views of scenes for exploring the appearance of advertisements and target objects in image frames of a video according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating a method for exploring advertisement delivery according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a client according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an advertisement delivery server according to an embodiment of the present invention.
Detailed Description
The in-frame advertisements (5S front advertisement, 15S rear advertisement, etc.) are video advertisements that are currently used. Taking 5S advertisement, it is a 5S advertisement displayed in a form of graphics, text or video before the video content is played.
The inventor finds that the existing in-frame advertisement is limited to single position and has low correlation with video content. For example, consider a scenario in which a certain brand of car appears in a video, and according to the current advertising method, a tile advertisement of the car is displayed before or after the video is played, and cannot be associated with the video content. Therefore, the attraction of the current in-frame advertisement is small, and the conversion rate is low.
In view of this, embodiments of the present invention provide an advertisement delivery method, an advertisement delivery server, a client, and an advertisement delivery system for exploring advertisements, so as to improve the relevance between advertisements and video content and diversify the delivery positions of advertisements.
Referring to fig. 1, the advertisement delivery system includes an advertisement delivery server and a client, where the client embeds an advertisement SDK to enable a user to display and explore an advertisement when watching a video using the client.
For simplicity, the number of ad serving servers and clients in fig. 1 is one each, and it is understood that the number of ad serving servers may be plural, and the number of clients may also be plural.
In the step of exploring the advertisement, the advertisement is rendered near a strongly-related target object in a specific scene of the video, and the advertisement can move along a path of the position of the target object, so that brand recognition is rapidly increased and conversion is promoted while viewing experience is not influenced.
The target object is an object appearing in the video, and a product corresponding to the search advertisement to be delivered by the advertiser. For example, if the advertiser is a certain brand of car, please refer to fig. 2, the car of the certain brand appearing in the image frame of the video is the target object.
In order to identify the target object in the image frame, please refer to fig. 1, an Artificial Intelligence (AI) system can be used to identify, track and locate the target object in the video. Of course, the AI system is trained in advance, for example, to recognize a car in an image, the AI system needs to be trained in advance to have the capability of recognizing the car.
To implement the discovery of the presentation of advertisements in videos, a certain amount of preliminary preparation is required, as described below, with reference to fig. 3, which illustratively includes:
s31: and the advertisement delivery service end provides the target video for the AI system.
The advertising service end can provide the target video to the AI system through the interface.
S32: and the AI system identifies the target object in the target video, generates a corresponding scene label and returns.
The scene tag includes: and the target appearance moment of the target object in the target video.
In addition, since the target object generally appears in the video for a certain period of time, that is, the target object may be included in continuous image frames.
A successive image frame containing a target object may be referred to as a slice.
Thus, the scene tag further includes: the appearance time (appearance moment) in each frame of image in the target video of the target object, the position coordinates (coordinates of four corner points of the minimum rectangle of the target object, namely the position coordinates), the size (accounting for one hundred percent of the screen), and the duration of appearance of continuous frames. The aforementioned target appearance time may be set as the first appearance time of the target object in the segment.
For the AI system, please refer to fig. 4a and 4b, which scans the video by the AI scene recognition technology, breaks the video segment into sequential frame images, identifies the appearance time, position coordinates, size (percentage of the screen), and duration of the appearance of the continuous frames in each image of the sequential frame, and marks the scene label based on the above information.
Specifically, the target video can be divided into sequence frames, feature points of each frame of picture are extracted, and feature matching is carried out on the feature points in the frame of picture and the feature points of the target object; then, based on the matched characteristic points, calculating a transformation matrix; and calculating the coordinate point of the target object based on the transformation matrix and the coordinate point of the marked frame image, and tracking the target object.
S33: and the advertisement delivery server receives the scene label and creates a corresponding advertisement protocol based on the scene label.
In one example, please refer to fig. 3 or fig. 4a and 4b, the scene tag may be first checked (typically manually) to see whether the point locations (the time of occurrence and the location coordinates) therein are accurate.
After the verification is passed, advertisements are created in the advertisement delivery system, scene labels matched with advertisement materials are selected, and a binding relationship is established between the delivery and the scene labels. Meanwhile, the advertisement delivery system also stores the binding relationship between the video identifier (generally, video ID) and the scene tag.
And generating an advertisement protocol bound with the scene label and activating the delivery.
Wherein the advertisement protocol at least comprises:
1, video identification of a target video;
2, the advertisement materials and rendering modes of the exploration advertisements associated with the target objects;
3, putting time information of putting segments of the advertisement materials;
the delivered segment is a segment including the target object in the target video. Also referred to as an ad slot.
The release time information comprises: and releasing the starting time and the duration of the segment in the target video, or releasing the starting time and the ending time of the segment in the target video.
4, the position and the size of the target object in each target launching frame in the launching section;
the target drop frame includes part or all of the image frames in the drop segment.
Further, the advertisement protocol may further include: and playing time information of the target release frame.
Specifically, the playing time information includes: at least one of a number of targeted delivery frames and a time interval between adjacent targeted delivery frames.
For example, assuming that the placement segment includes 100 image frames, 25 of the image frames can be selected as target placement frames for placement of the exploration advertisement. The playing time information may include the number of targeted delivery frames: 25, and the time interval for which the 25 frames of target frames are dropped. Therefore, the client side can determine the playing time of each target release frame in the release segment conveniently.
5, releasing period.
Typically in units of weeks or days.
And after the placement is activated, formally performing advertisement placement in a placement period. Referring to fig. 5, an exemplary method for exploring placement of advertisements by an advertisement placement system includes the steps of:
s51: and when the client opens the target video, sending a label pulling request to the advertisement putting server.
The tag pull request indicates at least a video identifier carrying the target video.
S52: and the advertisement delivery server returns the scene label corresponding to the video identifier to the client.
The scene tag includes: the target appearance time of the target object in the target video, and the like.
The scene tags can be referred to the above description, and are not described herein.
S53: the client sends an advertisement request to the advertisement delivery server in advance before the target occurrence time.
In one example, the SDK in the client may send the advertisement request to the advertisement delivery service a preset length of time (e.g., 5 seconds) in advance.
For example, assume that the target occurrence time is: 12 minutes, 48 seconds and 50ms, and an advertisement request can be sent to the advertisement delivery service end before the target video is played to 12 minutes, 43 seconds and 50ms or before.
The advertisement request may include a video identification of the target video and may also include a scene tag identification.
When the scene tag identification is globally unique, the advertisement request may only contain the scene tag identification.
S54: and the advertisement putting service end returns an advertisement protocol matched with the scene label to the client.
Wherein the returned advertisement protocol at least comprises: the method comprises the following steps of exploring advertisement materials of the advertisements related to the target objects, launching time information of launching sections of the advertisement materials, positions and sizes of the target objects in each target launching frame in the launching sections, and exploring rendering modes of the advertisements.
The release time information comprises: and releasing the starting time and the duration of the segment in the target video, or releasing the starting time and the ending time of the segment in the target video. For specific information, please refer to the above description, which is not repeated herein.
In one example, if the number of the advertisement protocols matched with the scene tag is multiple, a final advertisement protocol is screened out from the multiple advertisement protocols according to the screening condition, and the screened final advertisement protocol is returned.
Exemplary screening conditions include, but are not limited to: at least one of a placement priority and a directional territory.
Taking the directional region as an example, the directional region can be set for the advertisement protocol, after the region where the client is located is obtained, the region of the client and the directional region of the advertisement protocol can be matched, and the matched advertisement protocol is used as the final advertisement protocol.
And the advertisement protocols matched with regions are multiple, so that the final advertisement protocol can be screened out further according to the delivery priority of each matched advertisement protocol. And vice versa, the advertisement protocol with the highest priority can be screened and launched first, or the advertisement protocols with the highest priority are multiple, and region matching is further carried out to determine the final advertisement protocol.
S55: and when the target appearance moment of the target object of the release segment is reached, the client renders the exploration advertisement in each target release frame.
Specifically, the SDK of the client calculates a coordinate point for exploring advertisement rendering according to the position and size of the target object issued by the advertisement protocol, and displays an advertisement material in each target delivery frame based on the calculated coordinate point, rendering mode, and delivery time information.
In one example, if the advertisement protocol further includes the aforementioned play time information of the targeted frames (at least one of the number of targeted frames and the time interval between adjacent targeted frames);
then, according to the release time information and the play time information, each play time (i.e. corresponding target release frame) of each target release frame in the release segment can be determined. For example, assuming that the time interval of the target delivery frame is 5ms, the target occurrence time in the delivery time information is: 12 minutes, 48 seconds and 50ms, it can be determined that each playing time is 12 minutes, 48 seconds and 50ms, 12 minutes, 48 seconds and 55ms, 12 minutes, 48 seconds and 60ms, and so on.
And displaying the advertisement material in the currently displayed image frame based on the calculated coordinate point and the rendering mode at the determined playing time.
The following describes the advertisement material.
In the present embodiment, the advertising material may illustratively include, but is not limited to: text (advertising copy), lines, etc. In some examples, the advertising material may also include images or animations or videos. Advertisers can design advertising materials based on the information and mood delivered by the program, which is not described herein.
In addition, the advertisement material may also include a jump page to facilitate a jump when clicked by the user.
In this embodiment, the rendering manner may exemplarily include a rendering manner for a target object, a rendering manner for a text, and the like.
Exemplary target objects and rendering modes include, but are not limited to: a breathing frame and a rectangular frame.
The breathing frame is a small circle rendered in the center of the target object, and the small circle is circulated from big to small and from small to big like breathing.
The rectangular frame is a minimum rectangle containing the object, and 4 corner points are surrounded by lines.
The rendering mode of the text exemplarily includes: search bars, breath boxes (text in a box of varying size), etc.
For example, referring to the exploration advertisement shown in fig. 4a and 4b, the target object is a certain brand of car, the text in the advertisement material is "XX car is your convoy", and the rendering mode is a search bar mode. In fig. 4a and 4b, the small black spot in the center of the car is the breathing frame. The lines in the advertising material are connected with the search bar containing the copy.
How to calculate the coordinate points for exploring advertisement renderings is described below. In one example, the positions of the four corner points of the minimum rectangular frame of the target object under the image coordinates can be calculated according to the position and the size of the target object.
The positional relationship between the coordinate points of the advertisement material and the four corner points of the minimum rectangular frame of the target object may be pre-designed in the SDK, and the coordinate points (i.e., the display positions) of the advertisement material to be rendered may be calculated according to the pre-designed positional relationship.
After the calculation, it may further be determined whether the calculated display position is in the image frame, please refer to fig. 4b, where fig. 4b only shows a part of the target object, and the calculated display position to be rendered may also be outside the image. At this time, the display position may be adaptively adjusted by the SDK, for example, the display position is switched to the opposite side of the target object, but other adjustment methods may be used.
In addition, in other embodiments of the present invention, the advertisement material may further include: advertisement details, and advertisement details rendering.
The advertisement detail content rendering mode can be a playing control, such as a floating playing control.
Therefore, when the exploration advertisement appears, the user lightly touches the target object or the advertisement, the client SDK opens the control in a certain area of the video to display the detailed advertisement content according to the rendering mode of the detailed advertisement content on the premise of not pausing the video, and the rendering speed and experience of the method are better than those of the method of opening a jump-out webpage.
The area for displaying the playing control can be a fixed area and can also change along with the position of the target object. The calculation of the display coordinates of the display and play control component can refer to the calculation of the display coordinates of the advertisement material, and is not described herein again.
Therefore, in the embodiment of the invention, the exploration advertisement associated with the target object is put in the segment of the video where the target object appears, so that the relevance of the advertisement and the video content is increased. And the position of the target object in the video advertisement is determined according to the position of the target object in the video advertisement, and the video advertisement is not limited to be played before the head of the video or at the tail of the video. For example, referring to fig. 4a and 4b, the positions of the target object in frame n and frame n +10 are different, and the position of the advertisement for exploring moves, which produces the effect of moving along the moving path of the target object.
In the embodiment, the exploration advertisement is strongly related to the content of the video scene, and the user can be guided to explore the interested articles on the premise of not interrupting the watching behavior of the user. And the advertiser puts in the advertisement according to the information and the key that the program transmitted, promotes brand or commodity good feeling, deepens brand impression, promotes the conversion rate. Through video tagging, videos are enabled to have commercial value.
Considering that the time returned to the advertisement system when the target object is identified is incorrect when the film source is changed, in other embodiments of the present invention, the advertisement delivery method may further include the following steps:
after the film source of the target video is changed, the advertisement delivery server informs the AI system to acquire the target video at the new film source, re-identifies the target object in the target video (namely, triggers task re-running), generates a new scene label and returns;
the advertising serving base creates a corresponding new advertising agreement based on the new scenario tag.
How to generate new scene tags and how to create new advertisement protocols are similar to the foregoing and will not be described herein.
In addition, the time and the position of advertisement rendering are different from the appearance and disappearance time of the target object. The reason is that the time and the playing time of the advertisement SDK synchronized by the player are deviated, so that the advertisement SDK cannot be rendered at the absolutely correct time and position, and the solution is as follows:
reducing the deviation value between the playing time and the SDK time of the player (for example, reducing the difference value by using a third-party plug-in official recommendation mode), and controlling the deviation value to be 40-60 ms;
and b, compensating and correcting the deviation value by the advertisement SDK through an algorithm.
Embodiments of the present invention also claim a client (in particular an advertisement SDK), please see fig. 6, which exemplarily comprises:
a pulling unit 1 for:
sending a label pulling request to an advertisement putting server side when a target video is opened; the label pulls a video identifier carrying a target video; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label;
receiving a scene label corresponding to a video identifier of a target video phase; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
sending an advertisement request to an advertisement delivery server in advance before the target occurrence moment;
receiving an advertisement protocol returned by an advertisement delivery service end; the returned advertising protocol includes at least: exploring an advertisement material of the advertisement, launching time information of launching segments of the advertisement material, the position and the size of a target object in each target launching frame in the launching segments, and exploring a rendering mode of the advertisement; wherein, put in time information includes: the starting time and the duration of the fragments in the target video are launched, or the starting time and the ending time of the fragments in the target video are launched; the target release frame comprises part or all of the image frames in the release segment;
an exploring advertisement rendering unit 2 for:
and calculating a coordinate point for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate point, the rendering mode and the delivery time information.
For details, please refer to the above description, which is not repeated herein.
In other embodiments, the advertisement protocol may further include playing time information of the target delivery frame; wherein, the playing time information comprises: at least one of a number of targeted delivery frames and a time interval between adjacent targeted delivery frames.
Correspondingly, the exploration advertisement rendering unit 2 in the above embodiment is specifically configured to:
determining each playing time (namely the corresponding target release frame) of each target release frame in the release segment according to the release time information and the playing time information;
and displaying the advertisement material in the currently displayed image frame based on the calculated coordinate point and the rendering mode at the determined playing time.
For details, please refer to the above description, which is not repeated herein.
The invention also claims an advertisement delivery server, please refer to fig. 7, which exemplarily comprises:
a maintenance unit 3, configured to maintain the video identifier, the scene tag associated with the video identifier, and the advertisement protocol associated with the scene tag;
an advertisement delivery unit 4 configured to:
receiving a tag pull request; the label pulling request is sent when the client opens the target video; the label pulls a video identifier carrying a target video;
returning a scene label corresponding to the video identifier of the target video to the client; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
receiving an advertisement request; the advertisement request is sent by the client in advance before the target occurrence moment; the advertisement request comprises returned scene label identification;
returning an advertisement protocol matched with the scene label identification in the advertisement request to the client; the returned advertising protocol includes at least: exploring an advertisement material of the advertisement, launching time information of launching segments of the advertisement material, the position and the size of a target object in each target launching frame in the launching segments, and exploring a rendering mode of the advertisement; wherein, put in time information includes: the starting time and the duration of the fragments in the target video are launched, or the starting time and the ending time of the fragments in the target video are launched; the target release frame comprises part or all of the image frames in the release segment; the client is used for calculating coordinate points for exploring advertisement rendering according to the position and the size of a target object issued by the advertisement protocol, and displaying advertisement materials in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
For details, please refer to the above description, which is not repeated herein.
In another embodiment of the present invention, in terms of returning an advertisement agreement to a client, the advertisement delivery unit 4 is specifically configured to:
if the number of the advertisement protocols matched with the scene label identification is multiple, screening out a final advertisement protocol from the multiple advertisement protocols according to screening conditions;
returning the screened final advertisement protocol;
the screening condition includes at least one of a placement priority and a directional territory.
For details, please refer to the above description, which is not repeated herein.
In other embodiments of the present invention, before receiving the tag pull request, the maintenance unit 3 is further configured to:
providing a target video to an artificial intelligence recognition system; identifying a target object in a target video by an artificial intelligence identification system to generate a corresponding scene label;
and receiving the scene label returned by the artificial intelligence recognition system.
For details, please refer to the above description, which is not repeated herein.
In other embodiments of the present invention, before receiving the tag pulling request, after receiving the scene tag returned by the artificial intelligence recognition system, the maintenance unit 3 is further configured to:
and creating a corresponding advertising protocol based on the scene label.
For details, please refer to the above description, which is not repeated herein.
In other embodiments of the present invention, after the source of the target video is changed, the maintenance unit 3 is further configured to:
informing an artificial intelligence recognition system to obtain a target video at a new film source, re-recognizing a target object in the target video, generating a new scene label and returning;
a corresponding new advertising protocol is created based on the new scene tag.
For details, please refer to the above description, which is not repeated herein.
Those of skill would further appreciate that the various illustrative components and model steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. A skilled artisan may use different PFs for each particular application to implement the described functionality, but such implementation should not be considered beyond the scope of the present invention.
The steps of a PF or model described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, WD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. An advertisement discovery and placement method, based on an advertisement placement system, comprising: the system comprises an advertisement delivery server and a client; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label; the method comprises the following steps:
the advertisement delivery server receives a label pulling request; the label pulling request is sent when the client opens the target video; the label pulling request carries the video identification of the target video;
the advertisement delivery server returns a scene label corresponding to the video identifier of the target video to the client; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
the advertisement delivery server receives an advertisement request; the advertisement request is sent by the client in advance before the target occurrence moment; the advertisement request comprises returned scene label identification;
the advertisement delivery server side returns an advertisement protocol matched with the scene label identification in the advertisement request to the client side; the returned advertising protocol includes at least: the target object is associated with an advertisement material for exploring the advertisement, the launching time information of launching sections of the advertisement material, the position and the size of the target object in each target launching frame in the launching sections, and the rendering mode of the exploring advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment;
and the client is used for calculating coordinate points for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
2. The method of claim 1, wherein the advertising protocol further comprises play time information for targeted frames; wherein the playing time information includes: at least one of the number of target delivery frames and a time interval between adjacent target delivery frames; the playing time information is used for the client to determine the playing time of each target putting frame in the putting segment.
3. The method of claim 1,
the protocol of the advertisement delivery server returning the advertisement to the client comprises the following steps:
if the number of the advertisement protocols matched with the scene label identification is multiple, screening out a final advertisement protocol from the multiple advertisement protocols according to a screening condition;
returning the screened final advertisement protocol;
the screening condition includes at least one of a placement priority and a directional territory.
4. The method of claim 3, prior to receiving a tag pull request, further comprising:
the advertisement delivery server side provides the target video for an artificial intelligence recognition system; the artificial intelligence recognition system is used for recognizing the target object in the target video and generating a corresponding scene label;
and the advertisement delivery server receives the scene label returned by the artificial intelligence identification system.
5. The method of claim 4, wherein, after receiving the scene tag returned by the artificial intelligence recognition system prior to receiving the tag pull request, further comprising:
the advertising service end creates a corresponding advertising protocol based on the scene tag.
6. The method of claim 5, further comprising:
after the film source of the target video is changed, the advertisement delivery server informs the artificial intelligence recognition system to acquire the target video at a new film source, re-recognizes the target object in the target video, generates a new scene label and returns;
and the advertisement putting service end creates a corresponding new advertisement protocol based on the new scene label.
7. An advertisement discovery and placement method, based on an advertisement placement system, comprising: the system comprises an advertisement delivery server and a client; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label; the method comprises the following steps:
the client sends a label pulling request to the advertisement putting server when opening the target video; the label pulling request carries the video identification of the target video; the advertisement request comprises returned scene label identification;
the client receives a scene label corresponding to the target video; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
the client sends an advertisement request to the advertisement delivery server in advance before the target occurrence moment;
the client receives an advertisement protocol returned by the advertisement delivery server; the returned advertisement protocol includes at least: the target object is associated with advertisement material for exploring the advertisement, the launching time information of launching sections of the advertisement material, the position and the size of the target object in each target launching frame in the launching sections, and the rendering mode of the exploring advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment;
and the client calculates coordinate points for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displays the advertisement material in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
8. An advertisement delivery server, comprising:
a maintenance unit for maintaining the video identifier, the scene tag associated with the video identifier, and the advertisement protocol associated with the scene tag;
an advertisement delivery unit configured to:
receiving a tag pull request; the label pulling request is sent when the client opens the target video; the label pulling request carries the video identification of the target video;
returning a scene label corresponding to the video identifier of the target video to the client; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
receiving an advertisement request; the advertisement request is sent by the client in advance before the target occurrence moment; the advertisement request comprises returned scene label identification;
returning an advertisement protocol matched with the scene label identification in the advertisement request to the client; the returned advertising protocol includes at least: exploring an advertisement material of an advertisement, launching time information of launching sections of the advertisement material, a position and a size of the target object in each target launching frame in the launching sections, and exploring a rendering mode of the advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment; and the client is used for calculating coordinate points for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate points, the rendering mode and the delivery time information.
9. A client, characterized in that,
a pulling unit for:
sending a label pulling request to an advertisement putting server side when a target video is opened; the label pulling request carries the video identification of the target video; the advertisement delivery server side maintains a video identifier, a scene label associated with the video identifier and an advertisement protocol associated with the scene label;
receiving a scene label corresponding to the video identifier of the target video phase; wherein the returned scene tag at least comprises: the target appearance time of the target object in the target video; the target object includes: objects appearing in the target video;
sending an advertisement request to the advertisement delivery service terminal in advance before the target occurrence moment;
receiving an advertisement protocol returned by the advertisement delivery server; the returned advertisement protocol includes at least: exploring an advertisement material of an advertisement, launching time information of launching sections of the advertisement material, a position and a size of the target object in each target launching frame in the launching sections, and exploring a rendering mode of the advertisement; wherein the release time information includes: the starting time and the duration of the delivered segment in the target video, or the starting and ending time of the delivered segment in the target video; the target release frame comprises part or all of the image frames in the release segment;
an exploration advertisement rendering unit to:
and calculating a coordinate point for exploring advertisement rendering according to the position and the size of the target object issued by the advertisement protocol, and displaying the advertisement material in each target delivery frame based on the calculated coordinate point, the rendering mode and the delivery time information.
10. An advertisement delivery system comprising the advertisement delivery server according to claim 8 and the client according to claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110295684.2A CN113055732A (en) | 2021-03-19 | 2021-03-19 | Advertisement delivery method, advertisement delivery server, client and advertisement delivery system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110295684.2A CN113055732A (en) | 2021-03-19 | 2021-03-19 | Advertisement delivery method, advertisement delivery server, client and advertisement delivery system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113055732A true CN113055732A (en) | 2021-06-29 |
Family
ID=76513791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110295684.2A Pending CN113055732A (en) | 2021-03-19 | 2021-03-19 | Advertisement delivery method, advertisement delivery server, client and advertisement delivery system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113055732A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240478A (en) * | 2021-07-12 | 2021-08-10 | 深圳市清龙新能源有限公司 | Advertisement delivery device, method and system |
| CN114022189A (en) * | 2021-10-19 | 2022-02-08 | 百果园技术(新加坡)有限公司 | Advertisement display method and system based on page scene |
| CN114286175A (en) * | 2021-12-23 | 2022-04-05 | 天翼视讯传媒有限公司 | Method for playing video mosaic advertisement |
| US11593429B2 (en) * | 2018-03-21 | 2023-02-28 | Rovi Guides, Inc. | Systems and methods for presenting auxiliary video relating to an object a user is interested in when the user returns to a frame of a video in which the object is depicted |
| CN117217831A (en) * | 2023-11-08 | 2023-12-12 | 湖南快乐阳光互动娱乐传媒有限公司 | Advertisement putting method and device, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090259941A1 (en) * | 2008-04-15 | 2009-10-15 | Pvi Virtual Media Services, Llc | Preprocessing Video to Insert Visual Elements and Applications Thereof |
| CN102576441A (en) * | 2009-09-30 | 2012-07-11 | 微软公司 | Video content-aware advertisement placement |
| CN104170392A (en) * | 2013-11-21 | 2014-11-26 | 华为技术有限公司 | Method, device, system and terminal of inplanting advertisements in files |
-
2021
- 2021-03-19 CN CN202110295684.2A patent/CN113055732A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090259941A1 (en) * | 2008-04-15 | 2009-10-15 | Pvi Virtual Media Services, Llc | Preprocessing Video to Insert Visual Elements and Applications Thereof |
| CN102576441A (en) * | 2009-09-30 | 2012-07-11 | 微软公司 | Video content-aware advertisement placement |
| CN104170392A (en) * | 2013-11-21 | 2014-11-26 | 华为技术有限公司 | Method, device, system and terminal of inplanting advertisements in files |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11593429B2 (en) * | 2018-03-21 | 2023-02-28 | Rovi Guides, Inc. | Systems and methods for presenting auxiliary video relating to an object a user is interested in when the user returns to a frame of a video in which the object is depicted |
| CN113240478A (en) * | 2021-07-12 | 2021-08-10 | 深圳市清龙新能源有限公司 | Advertisement delivery device, method and system |
| CN114022189A (en) * | 2021-10-19 | 2022-02-08 | 百果园技术(新加坡)有限公司 | Advertisement display method and system based on page scene |
| CN114286175A (en) * | 2021-12-23 | 2022-04-05 | 天翼视讯传媒有限公司 | Method for playing video mosaic advertisement |
| CN117217831A (en) * | 2023-11-08 | 2023-12-12 | 湖南快乐阳光互动娱乐传媒有限公司 | Advertisement putting method and device, storage medium and electronic equipment |
| CN117217831B (en) * | 2023-11-08 | 2024-01-30 | 湖南快乐阳光互动娱乐传媒有限公司 | Advertisement putting method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113055732A (en) | Advertisement delivery method, advertisement delivery server, client and advertisement delivery system | |
| CN111698523B (en) | Method, device, equipment and storage medium for presenting text virtual gift | |
| US9930311B2 (en) | System and method for annotating a video with advertising information | |
| US20160050465A1 (en) | Dynamically targeted ad augmentation in video | |
| US10664703B2 (en) | Virtual trading card and augmented reality movie system | |
| WO2018036456A1 (en) | Method and device for tracking and recognizing commodity in video image and displaying commodity information | |
| KR101845473B1 (en) | Adaptively embedding visual advertising content into media content | |
| KR101760962B1 (en) | Video content-aware advertisement placement | |
| US20100086283A1 (en) | Systems and methods for updating video content with linked tagging information | |
| EP2046043B1 (en) | Dynamic replacement and insertion of cinematic stage props in program content | |
| CN109286824B (en) | Live broadcast user side control method, device, equipment and medium | |
| EP3425483B1 (en) | Intelligent object recognizer | |
| US20110184805A1 (en) | System and method for precision placement of in-game dynamic advertising in computer games | |
| US20180063599A1 (en) | Method of Displaying Advertisement of 360 VR Video | |
| US20180061130A1 (en) | Personalized video-based augmented reality | |
| US20120266189A1 (en) | System and method for delivering targeted advertisement messages | |
| JP2013535889A (en) | Method and apparatus for providing auxiliary content in a three-dimensional communication system | |
| US10406440B2 (en) | Method of collecting advertisement exposure data of 360 VR game replay video | |
| CN107770602A (en) | Method of video image processing and device | |
| CN111694983A (en) | Information display method, information display device, electronic equipment and storage medium | |
| US20200128284A1 (en) | System and method for providing an alert using tags on delivering digital content | |
| CN107770603B (en) | Video image processing method and device and terminal equipment | |
| US20110141359A1 (en) | In-Program Trigger of Video Content | |
| US20180310038A1 (en) | Dynamic content placement in media | |
| JP2020101847A (en) | Image file generator, method for generating image file, image generator, method for generating image, image generation system, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210629 |
|
| RJ01 | Rejection of invention patent application after publication |