CN117217831B - Advertisement putting method and device, storage medium and electronic equipment - Google Patents
Advertisement putting method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117217831B CN117217831B CN202311476920.6A CN202311476920A CN117217831B CN 117217831 B CN117217831 B CN 117217831B CN 202311476920 A CN202311476920 A CN 202311476920A CN 117217831 B CN117217831 B CN 117217831B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- video
- scene
- information
- vector
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 239000013598 vector Substances 0.000 claims abstract description 120
- 239000000463 material Substances 0.000 claims abstract description 106
- 238000012545 processing Methods 0.000 claims abstract description 23
- 239000012634 fragment Substances 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000002716 delivery method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an advertisement putting method and device, a storage medium and electronic equipment, wherein the method comprises the following steps: acquiring advertisement materials; analyzing the advertisement materials to obtain text description information corresponding to the advertisement materials; determining scene information of the advertising materials and bid information of advertising products corresponding to the advertising materials based on the text description information; processing the scene information to obtain a first scene vector corresponding to the scene information; searching at least one target video segment allowing advertisement materials to be put in a database based on the first scene vector; based on the bid information, determining effective video clips in which advertisement materials are put in each target video clip; advertisement material is added to each active video clip. According to the invention, advertisements are put through video scenes and bid information, so that the viewing experience of users is ensured, and the rights and interests of advertisers are also ensured.
Description
Technical Field
The present invention relates to the field of video processing technologies, and in particular, to a method and apparatus for advertisement delivery, a storage medium, and an electronic device.
Background
Information transmission in the form of video on the internet has become a common form, wherein, advertisements are taken as important ways for users to acquire information and advertisers to promote popularity and publicize products, and the information transmission has become normal by utilizing a method of inserting advertisements into the video.
In the prior art, advertisement delivery is usually performed at a blank position of a video so as to achieve the aim of advertisement exposure. However, the advertisement putting mode in the prior art cannot reasonably combine with video scenes to put advertisements, so that the watching experience of users is easily affected when advertisements are put in video scenes which are inconsistent with advertisement contents, and bid advertisements possibly exist in original videos even if the video scenes of the advertisements are proper, so that the rights and interests of advertisers are affected. Therefore, the advertisement putting mode in the prior art cannot guarantee the viewing experience of the user and cannot guarantee the rights and interests of advertisers at the same time.
Disclosure of Invention
In view of the above, the invention provides an advertisement putting method, by which advertisements can be put by combining video scenes and bid information, so that the viewing experience of users can be ensured, and the rights and interests of advertisers can be simultaneously ensured.
The invention also provides an advertisement putting device which is used for ensuring the realization and the application of the method in practice.
An advertising method comprising:
acquiring advertisement materials;
analyzing the advertisement materials to obtain text description information corresponding to the advertisement materials;
determining scene information for putting the advertisement materials and bid information of advertisement products corresponding to the advertisement materials based on the text description information;
processing the scene information to obtain a first scene vector corresponding to the scene information;
searching at least one target video segment allowing the advertisement material to be delivered in a database based on the first scene vector;
based on the bid information, determining effective video clips in which the advertisement materials are put in each target video clip;
and adding the advertisement materials to each effective video segment.
In the above method, optionally, the processing the scene information to obtain a first scene vector corresponding to the scene information includes:
and inputting the scene information into a preset Clip model to obtain a first scene vector corresponding to the scene information output by the Clip model.
In the above method, optionally, the searching at least one target video segment in the database that allows the advertisement material to be delivered based on the first scene vector includes:
calculating the similarity between the first scene vector and each second scene vector in a vector engine of the database, wherein the database stores a plurality of video clips, the vector engine comprises a second scene vector associated with each video clip, and the second scene vector is used for representing video scenes in the video clips associated with the second scene vector;
and determining the video segments corresponding to the second scene vectors with the similarity between the first scene vectors being greater than a first preset threshold as target video segments allowing the advertisement materials to be put in.
The method, optionally, further comprises:
acquiring a long video;
splitting the long video into a plurality of initial video segments;
extracting a first frame and a tail frame in each video frame of the initial video segment;
processing the first frame and the tail frame to obtain a first frame vector corresponding to the first frame and a tail frame vector corresponding to the tail frame;
and storing the initial video segment to the database under the condition that the similarity between the first frame vector and the tail frame vector is larger than a second preset threshold value.
The method, optionally, after storing the initial video segment in the database, further includes:
and storing the video frame vector corresponding to at least one video frame in the initial video segment as a second scene vector associated with the initial video segment to the vector engine.
In the above method, optionally, the determining, based on the bid information, an effective video segment in which the advertisement material is placed in each target video segment includes:
identifying first advertisement information in the target video segment;
determining whether an advertisement conforming to the bid information exists in the target video segment based on the first advertisement information;
and if the advertisement conforming to the bid information does not exist in the target video segment, determining that the target video segment is a valid video segment.
The above method, optionally, the adding the advertisement material in each of the effective video clips includes:
determining a target long video to which the effective video segment belongs;
identifying second advertisement information corresponding to the target long video;
determining whether the effective video segment meets preset advertisement delivery specifications or not based on the second advertisement information;
adding the advertisement materials into the effective video clips under the condition that the effective video clips accord with preset advertisement putting specifications;
the advertisement delivery specification is that the number of advertisements in a single video segment is smaller than a third threshold value, and the delivery time interval of the same advertisement material in the same long video is larger than a preset playing time.
An advertising device, comprising:
the acquisition unit is used for acquiring the advertisement materials;
the analysis unit is used for analyzing the advertisement materials and obtaining text description information corresponding to the advertisement materials;
the first determining unit is used for determining scene information for putting the advertisement materials and bid product information of advertisement products corresponding to the advertisement materials based on the text description information;
the processing unit is used for processing the scene information to obtain a first scene vector corresponding to the scene information;
the searching unit is used for searching at least one target video fragment which allows the advertisement material to be put in the database based on the first scene vector;
the second determining unit is used for determining effective video clips in which the advertisement materials are put in each target video clip based on the bid information;
and the advertisement putting unit is used for adding the advertisement materials into each effective video fragment.
A storage medium comprising stored instructions, wherein the instructions, when executed, control a device on which the storage medium resides to perform the advertising method described above.
An electronic device comprising a memory, and one or more instructions, wherein the one or more instructions are stored in the memory and configured to perform the advertising method described above by one or more processors.
Compared with the prior art, the invention has the following advantages:
the invention provides an advertisement putting method, which comprises the following steps: acquiring advertisement materials; analyzing the advertisement materials to obtain text description information corresponding to the advertisement materials; determining scene information for putting the advertisement materials and bid information of advertisement products corresponding to the advertisement materials based on the text description information; processing the scene information to obtain a first scene vector corresponding to the scene information; searching at least one target video segment allowing the advertisement material to be delivered in a database based on the first scene vector; based on the bid information, determining effective video clips in which the advertisement materials are put in each target video clip; and adding the advertisement materials to each effective video segment. The invention determines the video scene of the advertisement and the bid information of the bid of the advertisement by obtaining the text description of the advertisement material. The advertisements are put through the video scene and the bid information, so that the viewing experience of the user is guaranteed, and the rights and interests of advertisers can be guaranteed at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a method flow chart of an advertisement delivery method provided by an embodiment of the present invention;
FIG. 2 is a flowchart of another method of advertising method according to an embodiment of the present invention;
FIG. 3 is a flowchart of another method of advertising method according to an embodiment of the present invention;
FIG. 4 is a flowchart of another method of advertising method according to an embodiment of the present invention;
FIG. 5 is a block diagram of an advertisement delivery device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In this application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions, and the terms "comprise," "include," or any other variation thereof, are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The invention is operational with numerous general purpose or special purpose computing device environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor devices, distributed computing environments that include any of the above devices or devices, and the like.
The embodiment of the invention provides an advertisement putting method which can be applied to various system platforms, wherein an execution subject of the method can be a processor of a computer terminal or various mobile equipment, and a flow chart of the method is shown in fig. 1, and specifically comprises the following steps:
s101: and obtaining advertisement materials.
It should be noted that the advertisement material may be pictures, videos, texts, or the like.
S102: and analyzing the advertisement materials to obtain text description information corresponding to the advertisement materials.
Specifically, if the advertisement material is a picture or a video, the picture description generation technology is utilized to process the picture and the video of the advertisement material, and text description information corresponding to the advertisement material is obtained.
The picture or video is processed by using a picture description generation technology, specifically, a model obtained based on a deep learning method. Deep learning methods include attention mechanism-based methods, graph nerve-based methods, self-attention-based methods, and the like; the model is trained by a deep learning method, and is a visual Language Pre-training (VLP) model, a multi-modal Transformer (BLIP) model, a multi-modal Pre-training (One For All, OFA), a generated Pre-training transducer (generating Pre-Trained Transformer, GPT) model, chatGLM, or the like.
S103: based on the text description information, determining scene information of the advertising materials and bid information of advertising products corresponding to the advertising materials.
It should be noted that the scene information may be a scene text description that may be used to deliver advertisement materials. The bid information may include a bid picture, a bid name, and a textual description of the bid.
S104: and processing the scene information to obtain a first scene vector corresponding to the scene information.
Specifically, the scene information is processed through the Clip model, and a first scene vector corresponding to the scene information is obtained. The Clip model is an open source and widely used graphic and multimedia pre-training model for business.
S105: based on the first scene vector, at least one target video segment allowing advertisement materials to be delivered in the database is searched.
The database stores a plurality of video clips in advance, and each video clip is a short video clip divided by a long video in a mirror.
It should be further noted that, the database includes an index corresponding to each video clip, where the index is related to a video scene in the corresponding video clip, and the video clip corresponding to the scene information is searched for by using the first scene vector.
Specifically, based on the first scene vector, the implementation process of searching at least one target video segment in the database, which allows advertisement materials to be delivered, is as follows:
calculating the similarity between the first scene vector and each second scene vector in a vector engine of a database, wherein the database stores a plurality of video clips, the vector engine comprises the second scene vector associated with each video clip, and the second scene vector is used for representing the video scene in the video clip associated with the second scene vector;
and determining the video segments corresponding to the second scene vectors with the similarity between the first scene vectors being greater than a first preset threshold value as target video segments allowing advertisement materials to be put in.
It can be understood that a large number of video clips are stored in the database, and the video clips are video sub-lens segments after the long video is subjected to sub-lens processing. For each video segment in the database, corresponding index information is stored in the vector engine, and the index information is a second scene vector associated with the video segment. The second scene vector is the scene vector of its associated video segment. If the first scene vector is similar to the second scene vector, the video scenes in the video clips associated with the second scene vector are characterized as being suitable for playing the advertising material.
S106: based on the bid information, determining effective video clips for putting advertisement materials in each target video clip.
It can be appreciated that the target video segments which do not contain the bid are screened out as effective video segments through the bid information.
S107: advertisement material is added to each active video clip.
Optionally, when adding advertisement materials in the effective video clip, the video content can be identified, the dischargeable area and the non-dischargeable area can be distinguished, and the advertisement materials can be added in the dischargeable area. For example, the display area of characters, animals and other key objects is an undeliverable area, and the display area of characters, animals and other key objects is a jettisonable area.
In the method provided by the embodiment of the invention, a specific implementation process of storing advertisement video clips in a database is shown in fig. 2, and specifically includes:
s201: and acquiring a long video.
The long video may be a complete movie or a episode of a television series, etc.
S202: the long video is split into a plurality of initial video segments.
The long video is split according to the video splitting mode.
Specifically, the long video content which can participate in situation advertisement delivery is subjected to mirror division detection, the long video is divided into mirror-level video units, the mirror division is generally completed by adopting a pysceedelect library, and mirrors with the time length of the mirror division segments being greater than a certain threshold (for example, 5 seconds) are filtered. The segment duration of the split mirrors can be set empirically, in general, the split mirror segments can be smaller than 5 seconds, the split mirrors exceeding 5s occupy less total split mirrors, but there are more cases that gradual transition is possible in the middle: for example, the first 2 seconds are indoor, then one is blackened and one scene is lit up again.
S203: and extracting a first frame and a tail frame in each video frame of the initial video segment.
S204: and processing the first frame and the last frame to obtain a first frame vector corresponding to the first frame and a last frame vector corresponding to the last frame.
The video scene in the first frame is identified by adopting a Clip model, and a first frame vector is obtained; and identifying the video scene in the tail frame by adopting the Clip model to obtain a tail frame vector.
S205: and under the condition that the similarity between the first frame vector and the tail frame vector is larger than a second preset threshold value, storing the initial video segment into the database.
Vector similarity is calculated, and if the vector similarity is greater than a threshold value (for example, 0.7), a gradual change or long-distance mirror is considered to exist, and the vector similarity is marked as a segment unsuitable for advertising, and otherwise, the vector similarity is marked as a segment capable of advertising and is saved to a database.
Further, after determining that the video clip is stored in the database, a video frame vector corresponding to at least one video frame in the initial video clip may be stored as a second scene vector associated with the initial video clip to the vector engine.
Preferably, the video frame vector corresponding to the intermediate frame in the initial video segment may be selected and stored as an index to the vector engine, where the index is the second scene vector. And assuming that the segment has N frames, taking the N/2 th frame, and carrying out reasoning by using a Clip model to obtain vector characterization. And stores the vector in a vector engine for retrieval calculations.
In the method provided by the embodiment of the invention, based on the bid information, the process of determining the effective video segments in which the advertisement materials are put in each target video segment is shown in fig. 3, and specifically includes:
s301: first advertisement information in a target video segment is identified.
Specifically, first advertisement information appearing in the target video clip is detected by OCR technology and object detection technology.
S302: based on the first advertisement information, it is determined whether there is an advertisement in the target video segment that matches the bid information.
Specifically, in addition to the text description of the video clip, the bid information of the bid description may be obtained through the BLIP model. And determining whether a bid which conflicts with the advertisement material exists according to the first advertisement information and the bid information.
Wherein the bid information includes content that the customer specifies that the scene in which his advertisement is placed should not contain; the similar products of the advertisement products are maintained by self through the experience of advertisement putting, and the similar products are generally not allowed to appear, such as mobile phone advertisements, and other mobile phone contents are not allowed to appear; and associating the similar products through the capabilities of the BLIP model.
Wherein if there is no advertisement in the target video clip that matches the bid information, S303 is performed; otherwise, S304 is performed.
S303: and determining the target video segment as a valid video segment.
S304: and canceling the advertisement putting in the target video clip.
In the invention, the BLIP model can understand and output the scene description which can be matched with the advertisement and the text description which avoids the bid. And realizing the description of the advertisement material content by text information, and outputting content situation description and the same type of product description which accord with the advertisement delivery according to the text description so as to obtain video content situation description text for vector retrieval and product category information for avoiding the bid.
Further, after determining the valid video clips, the process of advertising in each valid video clip is shown in fig. 4, and specifically includes:
s401: and determining the target long video to which the effective video fragment belongs.
S402: and identifying second advertisement information corresponding to the target long video.
The second advertisement information comprises all advertisements of the long video including the effective video clips. The second advertisement information includes the first advertisement information.
S403: based on the second advertisement information, whether the effective video clip meets a preset advertisement delivery specification is determined.
The advertisement delivery specification is that the number of advertisements in a single video segment is smaller than a third threshold value, and the delivery time interval of the same advertisement material in the same long video is larger than a preset playing time.
In the embodiment of the invention, further screening is carried out according to the actual business: considering the balance of commercial interests and user experiences of advertisement delivery, it is first required that the advertisement delivery points in a single long video be spaced from the head by a certain period (e.g., 5 minutes from the time point of delivery), the number of occurrences of the contextual advertisements in a single long video should not be excessive (e.g., should not exceed 3), and the time intervals between two adjacent contextual advertisement delivery points should not be too close (e.g., should be more than 5 minutes). And comprehensively considering commercial interests of advertisement delivery, and expanding the number of covered video collections or reducing the number of video collections according to the interests.
S404: and adding advertisement materials into the effective video clips under the condition that the effective video clips accord with preset advertisement putting standards.
In the method provided by the embodiment of the invention, if the advertisement is too densely put in the whole long video, the viewing experience of the user is easily affected. Therefore, after any video segment in the long video is determined to be an effective video segment, whether the long video accords with the delivery specification or not is determined by combining second advertisement information in the whole long video, if so, advertisements can be directly added in the effective video segment, otherwise, the advertisements are canceled from being added in the effective video segment.
Optionally, when adding an advertisement in the effective video segment, identifying the advertisement position in the video segment, where the advertisement position may be four corners in the video or a position in the video segment where no key character exists.
By applying the method provided by the embodiment of the invention, through the advertisement delivery specification, the viewing experience of the user is considered, and meanwhile, the maximization of the income during advertisement delivery can be ensured.
Based on the method provided by the embodiment, the advertisement putting method provided by the invention has the following implementation contents:
and performing sub-mirror detection on the long video content, dividing the long video into sub-mirror level video units, and performing reasoning on the video sub-mirror segments by using a picture-text multi-mode pre-training model (Clip model) to obtain vector characterization. And stores the vector in a vector engine for retrieval calculations.
The material for advertisement delivery typically includes text, pictures or video, as well as textual descriptive material. The picture description generation technology is utilized to process advertisement material pictures and videos, and specifically, the large model (such as BLIP model and the like) capability is utilized to automatically generate video scene description texts and bid avoidance texts which adapt to advertisement contents. The picture description generation technology comprises the following steps: based on a deep learning method. The deep learning method comprises the following steps: attention-based methods, graph-based methods, self-attention-based methods, and other deep learning methods. The large model obtained by deep learning includes: VLP, BLIP, OFA, GPT or ChatGLM, etc.
And converting the advertisement adaptation video scene description text and the bid avoidance text extracted by the large model into vector representation through the Clip model, and carrying out similarity calculation with the long video mirror vector representation of the target. According to the service requirements, matched sub-lens segments in different long video collections and single long videos are required to be scattered, and dynamic similarity threshold adjustment is required to be carried out in the different long video collections and the single long videos according to the matching number and the time interval of the sub-lenses. The situation advertisement is ensured not to be too dense, so that the user viewing experience is affected. And finally obtaining all the points suitable for putting the situation advertisement.
According to the method, the positioning of the video content shot level and the scene level is realized by combining a text and image multi-mode pre-training model with a vector retrieval technology, the scene point position retrieval efficiency of the situation advertisement putting is improved, the limitation of the limited dimensionality and the dimensionality class set of the traditional AI analysis is broken through, and the free retrieval of any scene is realized. Thereby expanding the inventory of contextual advertising spots. The maximum possible mining of the contextual advertising value of massive long video inventory content.
The specific implementation process and derivative manner of the above embodiments are all within the protection scope of the present invention.
Corresponding to the method shown in fig. 1, the embodiment of the present invention further provides an advertisement delivery device, which is used for implementing the method shown in fig. 1, where the advertisement delivery device provided in the embodiment of the present invention may be applied to a computer terminal or various mobile devices, and the schematic structural diagram of the advertisement delivery device is shown in fig. 5, and specifically includes:
an acquisition unit 501 for acquiring advertisement materials;
the analysis unit 502 is configured to analyze the advertisement material and obtain text description information corresponding to the advertisement material;
a first determining unit 503, configured to determine, based on the text description information, scene information for delivering the advertisement material and bid information of an advertisement product corresponding to the advertisement material;
a processing unit 504, configured to process the scene information to obtain a first scene vector corresponding to the scene information;
a searching unit 505, configured to search at least one target video segment in a database that allows the advertisement material to be delivered based on the first scene vector;
a second determining unit 506, configured to determine, based on the bid information, an effective video segment in which the advertisement material is placed in each of the target video segments;
and an advertisement putting unit 507, configured to add the advertisement material to each of the active video clips.
In the apparatus provided by the embodiment of the present invention, the processing unit 504 processes the scene information, and the obtained first scene vector corresponding to the scene information is specifically used for:
and inputting the scene information into a preset Clip model to obtain a first scene vector corresponding to the scene information output by the Clip model.
In the apparatus provided in this embodiment of the present invention, the searching unit 505 searches, based on the first scene vector, at least one target video segment in a database that allows the advertisement material to be delivered, where the searching unit is specifically configured to:
calculating the similarity between the first scene vector and each second scene vector in a vector engine of the database, wherein the database stores a plurality of video clips, the vector engine comprises a second scene vector associated with each video clip, and the second scene vector is used for representing video scenes in the video clips associated with the second scene vector;
and determining the video segments corresponding to the second scene vectors with the similarity between the first scene vectors being greater than a first preset threshold as target video segments allowing the advertisement materials to be put in.
The device provided by the embodiment of the invention further comprises:
the video processing unit is used for acquiring long videos; splitting the long video into a plurality of initial video segments; extracting a first frame and a tail frame in each video frame of the initial video segment; processing the first frame and the tail frame to obtain a first frame vector corresponding to the first frame and a tail frame vector corresponding to the tail frame; and storing the initial video segment to the database under the condition that the similarity between the first frame vector and the tail frame vector is larger than a second preset threshold value.
In the apparatus provided by the embodiment of the present invention, after the video processing unit stores the initial video clip in the database, the video processing unit is further configured to:
and storing the video frame vector corresponding to at least one video frame in the initial video segment as a second scene vector associated with the initial video segment to the vector engine.
In the apparatus provided by the embodiment of the present invention, the second determining unit 506 determines, based on the bid information, an effective video segment in which the advertisement material is placed in each of the target video segments, where the effective video segment is specifically configured to:
identifying first advertisement information in the target video segment;
determining whether an advertisement conforming to the bid information exists in the target video segment based on the first advertisement information;
and if the advertisement conforming to the bid information does not exist in the target video segment, determining that the target video segment is a valid video segment.
In the device provided by the embodiment of the present invention, the advertisement putting unit 507 adds the advertisement material to each of the effective video clips, which is specifically configured to:
determining a target long video to which the effective video segment belongs;
identifying second advertisement information corresponding to the target long video;
determining whether the effective video segment meets preset advertisement delivery specifications or not based on the second advertisement information;
adding the advertisement materials into the effective video clips under the condition that the effective video clips accord with preset advertisement putting specifications;
the advertisement delivery specification is that the number of advertisements in a single video segment is smaller than a third threshold value, and the delivery time interval of the same advertisement material in the same long video is larger than a preset playing time.
The specific working process of each unit in the advertisement delivery device disclosed in the above embodiment of the present invention can be referred to the corresponding content in the advertisement delivery method disclosed in the above embodiment of the present invention, and will not be described herein again.
The embodiment of the invention also provides a storage medium, which comprises stored instructions, wherein the equipment where the storage medium is located is controlled to execute the advertisement putting method when the instructions run.
The embodiment of the present invention further provides an electronic device, whose structural schematic diagram is shown in fig. 6, specifically including a memory 601, and one or more instructions 602, where the one or more instructions 602 are stored in the memory 601, and configured to be executed by the one or more processors 603, where the one or more instructions 602 perform the following operations:
acquiring advertisement materials;
analyzing the advertisement materials to obtain text description information corresponding to the advertisement materials;
determining scene information for putting the advertisement materials and bid information of advertisement products corresponding to the advertisement materials based on the text description information;
processing the scene information to obtain a first scene vector corresponding to the scene information;
searching at least one target video segment allowing the advertisement material to be delivered in a database based on the first scene vector;
based on the bid information, determining effective video clips in which the advertisement materials are put in each target video clip;
and adding the advertisement materials to each effective video segment.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for a system or system embodiment, since it is substantially similar to a method embodiment, the description is relatively simple, with reference to the description of the method embodiment being made in part. The systems and system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
Those of skill would further appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
To clearly illustrate this interchangeability of hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
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 (9)
1. An advertising method, comprising:
acquiring advertisement materials;
analyzing the advertisement materials to obtain text description information corresponding to the advertisement materials;
determining scene information for putting the advertisement materials and bid information of advertisement products corresponding to the advertisement materials based on the text description information;
processing the scene information to obtain a first scene vector corresponding to the scene information;
searching at least one target video segment allowing the advertisement material to be delivered in a database based on the first scene vector;
identifying first advertisement information in the target video segment;
determining whether an advertisement conforming to the bid information exists in the target video segment based on the first advertisement information;
if the target video segment does not have the advertisement conforming to the bid information, determining the target video segment as an effective video segment;
and adding the advertisement materials to each effective video segment.
2. The method according to claim 1, wherein the processing the scene information to obtain a first scene vector corresponding to the scene information includes:
and inputting the scene information into a preset Clip model to obtain a first scene vector corresponding to the scene information output by the Clip model.
3. The method of claim 1, wherein the looking up at least one target video segment in a database that allows delivery of the advertising material based on the first scene vector comprises:
calculating the similarity between the first scene vector and each second scene vector in a vector engine of the database, wherein the database stores a plurality of video clips, the vector engine comprises a second scene vector associated with each video clip, and the second scene vector is used for representing video scenes in the video clips associated with the second scene vector;
and determining the video segments corresponding to the second scene vectors with the similarity between the first scene vectors being greater than a first preset threshold as target video segments allowing the advertisement materials to be put in.
4. A method according to claim 3, further comprising:
acquiring a long video;
splitting the long video into a plurality of initial video segments;
extracting a first frame and a tail frame in each video frame of the initial video segment;
processing the first frame and the tail frame to obtain a first frame vector corresponding to the first frame and a tail frame vector corresponding to the tail frame;
and storing the initial video segment to the database under the condition that the similarity between the first frame vector and the tail frame vector is larger than a second preset threshold value.
5. The method of claim 4, wherein after saving the initial video segment to the database, further comprising:
and storing the video frame vector corresponding to at least one video frame in the initial video segment as a second scene vector associated with the initial video segment to the vector engine.
6. The method of claim 1, wherein said adding said advertising material in each of said active video clips comprises:
determining a target long video to which the effective video segment belongs;
identifying second advertisement information corresponding to the target long video;
determining whether the effective video segment meets preset advertisement delivery specifications or not based on the second advertisement information;
adding the advertisement materials into the effective video clips under the condition that the effective video clips accord with preset advertisement putting specifications;
the advertisement delivery specification is that the number of advertisements in a single video segment is smaller than a third threshold value, and the delivery time interval of the same advertisement material in the same long video is larger than a preset playing time.
7. An advertising device, comprising:
the acquisition unit is used for acquiring the advertisement materials;
the analysis unit is used for analyzing the advertisement materials and obtaining text description information corresponding to the advertisement materials;
the first determining unit is used for determining scene information for putting the advertisement materials and bid product information of advertisement products corresponding to the advertisement materials based on the text description information;
the processing unit is used for processing the scene information to obtain a first scene vector corresponding to the scene information;
the searching unit is used for searching at least one target video fragment which allows the advertisement material to be put in the database based on the first scene vector;
a second determining unit, configured to identify first advertisement information in the target video segment; determining whether an advertisement conforming to the bid information exists in the target video segment based on the first advertisement information; if the target video segment does not have the advertisement conforming to the bid information, determining the target video segment as an effective video segment;
and the advertisement putting unit is used for adding the advertisement materials into each effective video fragment.
8. A storage medium comprising stored instructions, wherein the instructions, when executed, control a device in which the storage medium is located to perform the advertisement delivery method according to any one of claims 1 to 6.
9. An electronic device comprising a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by the one or more processors to perform the method of advertising as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311476920.6A CN117217831B (en) | 2023-11-08 | 2023-11-08 | Advertisement putting method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311476920.6A CN117217831B (en) | 2023-11-08 | 2023-11-08 | Advertisement putting method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117217831A CN117217831A (en) | 2023-12-12 |
| CN117217831B true CN117217831B (en) | 2024-01-30 |
Family
ID=89037485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311476920.6A Active CN117217831B (en) | 2023-11-08 | 2023-11-08 | Advertisement putting method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117217831B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005017950A (en) * | 2003-06-27 | 2005-01-20 | Nippon Telegr & Teleph Corp <Ntt> | Advertisement information distribution method and advertisement information distribution system |
| CN103313132A (en) * | 2013-06-20 | 2013-09-18 | 天脉聚源(北京)传媒科技有限公司 | Television advertisement information publishing method and system |
| CN104902345A (en) * | 2015-05-26 | 2015-09-09 | 多维新创（北京）技术有限公司 | Method and system for realizing interactive advertising and marketing of products |
| WO2018107914A1 (en) * | 2016-12-16 | 2018-06-21 | 中兴通讯股份有限公司 | Video analysis platform, matching method, and accurate advertisement push method and system |
| WO2018121554A1 (en) * | 2016-12-29 | 2018-07-05 | 腾讯科技（深圳）有限公司 | Information processing method, information processing device, and storage medium |
| CN111738769A (en) * | 2020-06-24 | 2020-10-02 | 湖南快乐阳光互动娱乐传媒有限公司 | Video processing method and device |
| CN113055732A (en) * | 2021-03-19 | 2021-06-29 | 湖南快乐阳光互动娱乐传媒有限公司 | Advertisement delivery method, advertisement delivery server, client and advertisement delivery system |
| KR20210153324A (en) * | 2020-06-10 | 2021-12-17 | (주)커넥트온 | Method for providing advertisement service to prevent exposure of competitive advertisement and system therefore |
| CN115018551A (en) * | 2022-06-29 | 2022-09-06 | 北京飞天经纬科技股份有限公司 | CRM data management method and device for advertisement service and storage medium |
| CN115293793A (en) * | 2022-07-01 | 2022-11-04 | 北京明略昭辉科技有限公司 | Advertisement putting method and device, readable medium and electronic equipment |
| CN116071110A (en) * | 2022-12-30 | 2023-05-05 | 深圳市千岩科技有限公司 | Advertisement creation method, advertisement creation device and storage medium |
| CN116614652A (en) * | 2023-06-07 | 2023-08-18 | 中国联合网络通信集团有限公司 | Advertisement video clip replacement method, device and storage medium in live broadcast scene |
-
2023
- 2023-11-08 CN CN202311476920.6A patent/CN117217831B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005017950A (en) * | 2003-06-27 | 2005-01-20 | Nippon Telegr & Teleph Corp <Ntt> | Advertisement information distribution method and advertisement information distribution system |
| CN103313132A (en) * | 2013-06-20 | 2013-09-18 | 天脉聚源(北京)传媒科技有限公司 | Television advertisement information publishing method and system |
| CN104902345A (en) * | 2015-05-26 | 2015-09-09 | 多维新创（北京）技术有限公司 | Method and system for realizing interactive advertising and marketing of products |
| WO2018107914A1 (en) * | 2016-12-16 | 2018-06-21 | 中兴通讯股份有限公司 | Video analysis platform, matching method, and accurate advertisement push method and system |
| WO2018121554A1 (en) * | 2016-12-29 | 2018-07-05 | 腾讯科技（深圳）有限公司 | Information processing method, information processing device, and storage medium |
| KR20210153324A (en) * | 2020-06-10 | 2021-12-17 | (주)커넥트온 | Method for providing advertisement service to prevent exposure of competitive advertisement and system therefore |
| CN111738769A (en) * | 2020-06-24 | 2020-10-02 | 湖南快乐阳光互动娱乐传媒有限公司 | Video processing method and device |
| CN113055732A (en) * | 2021-03-19 | 2021-06-29 | 湖南快乐阳光互动娱乐传媒有限公司 | Advertisement delivery method, advertisement delivery server, client and advertisement delivery system |
| CN115018551A (en) * | 2022-06-29 | 2022-09-06 | 北京飞天经纬科技股份有限公司 | CRM data management method and device for advertisement service and storage medium |
| CN115293793A (en) * | 2022-07-01 | 2022-11-04 | 北京明略昭辉科技有限公司 | Advertisement putting method and device, readable medium and electronic equipment |
| CN116071110A (en) * | 2022-12-30 | 2023-05-05 | 深圳市千岩科技有限公司 | Advertisement creation method, advertisement creation device and storage medium |
| CN116614652A (en) * | 2023-06-07 | 2023-08-18 | 中国联合网络通信集团有限公司 | Advertisement video clip replacement method, device and storage medium in live broadcast scene |
Non-Patent Citations (2)
| Title |
|---|
| 基于不同竞品干扰环境下的新品平面广告设计方案效果的眼动测评;王士龙;;东南传播(第11期);第140-142页 * |
| 基于细粒度标签的在线视频广告投放机制研究;陆枫;王子锐;廖小飞;金海;;计算机研究与发展(第12期);第151-163页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117217831A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378732B (en) | Information display method, information association method, device, equipment and storage medium | |
| US9466068B2 (en) | System and method for determining a pupillary response to a multimedia data element | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN110134931B (en) | Medium title generation method, medium title generation device, electronic equipment and readable medium | |
| US9043860B2 (en) | Method and apparatus for extracting advertisement keywords in association with situations of video scenes | |
| JP2019212290A (en) | Method and device for processing video | |
| CN105453122A (en) | Contextual mobile application advertisements | |
| US10210257B2 (en) | Apparatus and method for determining user attention using a deep-content-classification (DCC) system | |
| CN110347866B (en) | Information processing method, information processing device, storage medium and electronic equipment | |
| CN111177467A (en) | Object recommendation method and device, computer-readable storage medium and electronic equipment | |
| CN111444387A (en) | Video classification method and device, computer equipment and storage medium | |
| CN113824972A (en) | Live video processing method, device and equipment and computer readable storage medium | |
| CN115907868A (en) | Advertisement delivery analysis method and device | |
| US20200057821A1 (en) | Generating a platform-based representative image for a digital video | |
| CN117217831B (en) | Advertisement putting method and device, storage medium and electronic equipment | |
| KR101174119B1 (en) | System and method for advertisement | |
| KR102560610B1 (en) | Reference video data recommend method for video creation and apparatus performing thereof | |
| CN113537127A (en) | Film matching method, device, equipment and storage medium | |
| CN113515670A (en) | Method, device and storage medium for identifying state of movie and television resource | |
| KR20210093743A (en) | Method and apparatus for providing media enrichment | |
| CN113450134A (en) | Advertisement putting method, device, equipment and storage medium | |
| KR20220022767A (en) | System and method for analyzing advertisement | |
| CN111127079A (en) | Method, device, computer equipment and storage medium for issuing commodity resources | |
| KR20160091488A (en) | Method and System for Automatic Detection of Object using Model Generation | |
| CN113709529B (en) | Video synthesis method, device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |