CN115187301A - Advertisement instant implanting method, system and device based on user portrait - Google Patents
Advertisement instant implanting method, system and device based on user portrait Download PDFInfo
- Publication number
- CN115187301A CN115187301A CN202210824245.0A CN202210824245A CN115187301A CN 115187301 A CN115187301 A CN 115187301A CN 202210824245 A CN202210824245 A CN 202210824245A CN 115187301 A CN115187301 A CN 115187301A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- data
- product
- scene
- purchased
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2228—Indexing structures
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method, a system and a device for instantly implanting advertisements based on user portrait comprise the steps of constructing a user portrait label model, matching corresponding products in a product database according to product preference model labels, accessing to a corresponding advertisement database when monitoring a video resource access request of a user side, matching corresponding advertisement delivery data in the advertisement database, determining the matched data as advertisement data to be implanted, performing scene traversal on the current video resource to perform scene suitability judgment on the advertisement data to be implanted, performing frame-by-frame traversal on each scene according to a scene sequence to search image blocks suitable for implantation, and extracting matched advertisement images from the corresponding advertisement data to be implanted to implant the advertisement images in the image blocks; the method can implant advertisements which accord with the portrait of the user into the accessed video resources according to the video resource access requests of different users, and generate different advertisement implantation effects aiming at the access of different video resources, thereby realizing the accurate and instant implantation of the advertisements.
Description
Technical Field
The invention relates to the technical field of advertisement implantation, in particular to a method, a system and a device for implanting advertisements in real time based on user portrait.
Background
"Product Placement" refers to an advertising method that incorporates audiovisual brand symbols representative of products and their services into movie or stage works, and gives viewers considerable impression for marketing purposes. The "embedded advertisement" is an advertisement form which is developed along with the development of movies, televisions, games and the like, and means that products or services of merchants are deliberately inserted into movie and television scenarios and games so as to achieve the latent and acquiescent propaganda effect. Because the audience has an inherent conflicting mind on advertising, incorporating merchandise into these entertainment modes is often much more effective than hard promotions.
In the prior art, for example, a Video in dynamic advertisement implantation technology proposed by a certain Video website provides a technical solution for performing secondary content synthesis in a photographed Video, that is, an advertisement entity can be naturally implanted into an original Video scene in a post-processing process. This means that the in-line advertising will no longer be limited by the movie capture cycle, and the "Video in" technology will make the in-line advertising sale cycle and content life cycle equally long. The video entity advertisement implantation technical difficulty is that after a real object is synthesized into a video picture, high-fidelity adjustment conforming to the original picture must be carried out on illumination, shielding, shadow distribution and texture definition of the surface of the real object, otherwise, a user can obviously feel the incompatibility of the synthesized object and the whole environment, and the user experience is seriously influenced. The 'Video in' technology can finely analyze the contour curved surface, the size, the shielding, the light reflection rate, the light source position coordinate, the color component and the like of the implanted real object, calculate the model parameters and implant the high fidelity.
With the development of artificial intelligence technology, the advertisement placement technology is also pushed towards more intelligent direction, such as analyzing the video content through AI technology to find the position where the advertisement is likely to be placed in the picture, and then modeling and rendering automatically. Even the influence factors of the character motion relation, the light effect and the like appearing in the picture can be taken into consideration. Some involve dynamic advertisement placement, and the AI also analyzes the trajectory of the vehicle and the process of the sudden billboard from far to near. The combination of the image processing and AI technologies of the film special effect technology creates a huge post-implantation advertisement market unintentionally.
However, there is a certain technical gap in the advertisement placement technology exemplified above, which is specifically embodied in that: the advertisements planted in the video are from the placement of specific clients and belong to the placement behavior under the business cooperation, so that the advertisements planted in a movie or a video resource are specific and do not consider the receptivity of different user groups, so that the accurate placement of the advertisements is difficult to achieve; in the later stage of advertisement placement based on advertisement pursuit, due to the time difference, the coverage of the user is limited, and the user who has viewed a certain video resource belongs to an invalid placement behavior.
Disclosure of Invention
The purpose of the invention is as follows:
in order to overcome the drawbacks indicated in the background art, embodiments of the present invention provide a method, system and apparatus for instantly implanting an advertisement based on a user profile, which can effectively solve the problems related to the background art.
The technical scheme is as follows:
an advertisement instant placement method based on a user profile, the method comprising the steps of: constructing a user portrait label model according to user behavior data, wherein the user portrait label model at least comprises a product preference model label; matching corresponding products in a product database according to the product preference model labels and creating product indexes according to product categories; when a video resource access request of a user side is monitored, a database access request is sent to the video resource side to access an advertisement database corresponding to the video resource; performing corresponding advertisement putting data matching in the advertisement database according to the product index and determining the matched advertisement putting data as advertisement data to be implanted; performing scene traversal on the current video resource to generate a scene label, performing scene applicability judgment on the advertisement data to be implanted, and establishing a mapping relation between the scene label and the advertisement data to be implanted according to a judgment result; and traversing each scene frame by frame according to the sequence of the scenes to search for image blocks suitable for implantation, and extracting matched advertisement images from the corresponding advertisement data to be implanted to implant the advertisement images into the image blocks.
As a preferable mode of the present invention, the method further comprises the steps of:
acquiring products to be purchased of a user side in an e-commerce platform, wherein the products to be purchased comprise shopping cart products and collected products; and matching corresponding advertisement putting data in the advertisement database according to the product to be purchased, and determining the matched advertisement putting data as the advertisement data to be implanted when a matching result exists.
As a preferred mode of the present invention, if there is no matching result, the method further includes the steps of: acquiring advertisement enrollment requirements of the video resource end and advertisement release data of the product to be purchased, wherein the advertisement enrollment requirements at least comprise charging information, and the advertisement release data at least comprise budget information; judging whether the advertisement putting data of the product to be purchased meet the advertisement enrollment requirement or not; if yes, automatically performing advertisement putting subscription on the product to be purchased and the video resource end, and determining the advertisement putting data of the product to be purchased as advertisement data to be implanted.
As a preferred mode of the present invention, the method further comprises the steps of: performing bullet screen traversal on each scene to sequence bullet screen quantities; and traversing each scene frame by frame according to the bullet screen amount sequencing to search image blocks suitable for implantation.
A user profile based advertisement placement system, the system comprising: the tag model building module is used for building a user portrait tag model according to user behavior data, wherein the user portrait tag model at least comprises a product preference model tag; the product matching module is used for matching corresponding products in a product database according to the product preference model labels; the index creating module is used for creating a product index according to the product category; the database access module is used for sending a database access request to the video resource end to access an advertisement database corresponding to the video resource when monitoring a video resource access request of a user end; the first advertisement matching module is used for matching corresponding advertisement putting data in the advertisement database according to the product index and determining the matched advertisement putting data as advertisement data to be implanted; the scene traversal module is used for performing scene traversal on the current video resource to generate a scene label; the scene suitability judging module is used for carrying out scene suitability judgment on the advertisement data to be implanted; the mapping relation establishing module is used for establishing the mapping relation between the scene label and the advertisement data to be implanted according to the result of judging the scene applicability of the advertisement data to be implanted; the first image block searching module is used for traversing each scene frame by frame according to the scene sequence so as to search an image block suitable for implantation; and the advertisement implanting module is used for extracting a matched advertisement image from the corresponding advertisement data to be implanted so as to implant the advertisement image into the image block.
As a preferred mode of the present invention, the system further includes: the system comprises a to-be-purchased product acquisition module, a to-be-purchased product acquisition module and a to-be-purchased product acquisition module, wherein the to-be-purchased product acquisition module is used for acquiring a to-be-purchased product of a user side in an e-commerce platform, and the to-be-purchased product comprises a shopping cart product and a collected product; and the second advertisement matching module is used for matching corresponding advertisement putting data in the advertisement database according to the product to be purchased and determining the matched advertisement putting data as the advertisement data to be implanted when a matching result exists.
As a preferred mode of the present invention, the system further includes: the data acquisition module is used for acquiring the advertising enrollment demand of the video resource end and the advertising data of the product to be purchased when no matching result exists when corresponding advertising data matching is carried out in the advertising database according to the product to be purchased, wherein the advertising enrollment demand at least comprises charging information, and the advertising data at least comprises budget information; the enrollment requirement judging module is used for judging whether the advertisement putting data of the product to be purchased meet the advertisement enrollment requirement; and the advertisement signing module is used for automatically carrying out advertisement putting signing on the product to be purchased and the video resource end when the advertisement putting data of the product to be purchased meet the advertisement putting demand, and determining the advertisement putting data of the product to be purchased as the advertisement data to be implanted.
As a preferred mode of the present invention, the system further includes: the bullet screen traversal module is used for performing bullet screen traversal on each scene so as to sequence bullet screen quantities; and the second image block searching module is used for traversing each scene frame by frame according to the bullet screen amount sequence so as to search the image block suitable for implantation.
An advertisement instant placement device based on a user representation, comprising: a memory for storing a computer program and a processor for invoking the computer program to perform a user portrait based advertisement instant placement method as described above.
The invention realizes the following beneficial effects:
1. through the implementation of the invention, namely, a user portrait label model is constructed, corresponding products are matched in a product database according to product preference model labels, an advertisement database corresponding to video resources is accessed when a video resource access request of a user end is monitored, corresponding advertisement delivery data matching is carried out in the advertisement database, the matched advertisement delivery data is determined as advertisement data to be implanted, scene traversal is carried out on the current video resources to carry out scene suitability judgment on the advertisement data to be implanted, each scene is traversed frame by frame according to a scene sequence to search an image block suitable for implantation, and a matched advertisement image is extracted from the corresponding advertisement data to be implanted in the image block; therefore, the advertisements which are in accordance with the user figures can be implanted into the accessed video resources according to the video resource access requests of different users, different advertisement implantation effects are generated aiming at the access of different video resources, and the accurate and instant implantation of the advertisements is realized.
2. By implementing the invention, the video resource access requests of different users can be implanted with advertisements which meet the actual purchase requirements of the video resources accessed by the users, thereby widening the range of implanted advertisements.
3. By the implementation of the method and the device, the advertisement implantation can be preferentially carried out on the scene with the bullet screen amount ahead, so that the marketing effect of the advertisement implantation is improved.
Drawings
FIG. 1 is a flow chart illustrating a method for real-time advertisement placement based on a user representation according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a method for determining advertisement data to be implanted according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of another method for determining advertisement data to be implanted according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for finding a suitable implant image block according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a user representation-based advertisement instant placement system according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an advertisement instant insertion device based on a user representation according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present invention and should not be construed as limiting the present invention.
Referring to fig. 1 and 5, the present embodiment provides a method for instantly implanting an advertisement based on a user profile, which includes steps S10 to S16, and the steps included in the method are described below.
S10, constructing a user portrait label model 502 according to the user behavior data, wherein the user portrait label model 502 at least comprises a product preference model label.
The user behavior data comprises static behavior data and dynamic behavior data, wherein the static behavior data mainly refers to user identity information, such as gender, age, occupation, marital state, family membership and the like; the dynamic behavior data refers to behavior data generated by the user at the user end 507, such as browsing records, searching records, downloading records, operation data of social networks and e-commerce websites, and is acquired by accessing an application program and a web page to collect log data, service data, and third-party data. After user behavior data is acquired, the data needs to be cleaned, namely, repeated and redundant data is screened and removed, missing data is completely supplemented, and wrong data is corrected or deleted and finally arranged into data which can be further processed and used; then analyzing the user behavior data through a big data algorithm to label the user to construct a user portrait label model 502; since the specific big data algorithm analysis and modeling process belongs to the prior art knowledge, the description is not carried out in the specification, and the user portrait label model 502 which needs to be explained, namely constructed, at least comprises a product preference model label. And the product preference model labels are subjected to priority sorting according to the weight values corresponding to the items.
S11, matching corresponding products in the product database 504 according to the product preference model labels and creating product indexes according to product categories.
The product database is a real-time product catalog acquired on an e-commerce website through a crawler tool and generates a database stored locally; or the product information can be obtained from the e-commerce website in real time through a data access interface (the product database 504 in this way is the e-commerce website).
The product preference model tag may be a specific product name (for example, may include a brand, a model, and the like to which a product belongs), or may be a fuzzy expression, and if the product preference model tag is the specific product name, the product preference model tag is directly searched for in the product database 504 by accurate matching according to the product name, and if the product preference model tag is the fuzzy expression, the product preference model tag is searched for in the product database 504 by corresponding searching according to a keyword thereof, and after related product data is searched for, the related product preference model tag is clustered according to a product category, and a product index is created.
In one embodiment, the user representation tag model 502 includes a consumption capability tag, and matches and screens product data in the product database 504 in combination with the consumption capability tag of the user, and rejects product data that does not match with the consumption capability tag; the consumer capability label is, for example, a price interval.
In some embodiments, as an alternative to S11, matching corresponding products in product database 504 based on other model tags in user representation tag model 502 and creating a product index based on product category.
S12, when monitoring a video resource access request of the user end 507, sending a database access request to the video resource end 508 to access the advertisement database 509 corresponding to the video resource.
The video resource end 508 is a server end corresponding to a platform (web page, application program) where the video resource is located; the advertisement database 509 stores data including advertisements placed in the video resources, and the advertisement database 509 may be expanded to correspond to a platform where the video resources are located and include advertisement data placed in all video resources under the platform.
The sending condition of the video resource access request is that when it is monitored that a video resource play button is triggered (including manual triggering and automatic triggering), the user end 507 sends a database access request to the video resource end 508, the database access request carries page information (for example, a URL) of the video resource triggered by the play button, and when receiving the database access request sent by the user end 507, the video resource end 508 opens an access interface of the advertisement database 509 corresponding to the video resource to the user end 507 by reading the page information of the video resource carried by the video resource end 508 so that the user end 507 accesses the advertisement database 509 corresponding to the video resource.
S13, matching corresponding advertisement putting data in the advertisement database 509 according to the product index and determining the matched advertisement putting data as advertisement data to be implanted.
Specifically, the advertisement delivery data in the advertisement database 509 is matched with the product index, which can be understood as identifying the product category to which the advertisement delivery data belongs and comparing the product category with the product index, and if the comparison is successful, the matched advertisement delivery data is determined as the advertisement data to be implanted; in one embodiment, after successful matching, the product covered by the product index is further accurately compared with the advertisement delivery data in the advertisement database 509, and the advertisement delivery data successfully compared is determined as the advertisement data to be implanted.
And S14, performing scene traversal on the current video resource to generate a scene label.
Specifically, the user end 507 sends a video resource library access request to the video resource end 508 to access the video resource library corresponding to the video resource, so as to quickly obtain a video source corresponding to the video resource, quickly preview and traverse all scenes in the video resource, and generate a label, i.e., a scene label, for the scene.
Practical examples are as follows: the user end 507 monitors that a video resource play button of a certain episode of a television play with a time length of 40 minutes is triggered on a certain video website, and after a video source corresponding to the video resource is acquired, fast previews the video resource and traverses all scenes of the video resource to generate a scene tag, as follows:
| sequence of scenes | Scene time | Scene label |
| 1 | 0:00-2:30 | Indoor; a living room; a sofa; a dining table; white wall |
| 2 | 2:31-5:08 | Outdoors; a bicycle; a backpack; a bus; |
| 3 | 5:09-7:23 | indoor; an elevator; an office table; display device |
| … | … | … |
The scene labels are only examples, and labels generated based on the actual state of the scene are different; in one embodiment, the client 507 further obtains a scenario introduction corresponding to the video resource to generate a scene tag.
S15, scene applicability judgment is carried out on the advertisement data to be implanted, and a mapping relation between the scene label and the advertisement data to be implanted is established according to a judgment result.
When the scene applicability judgment is carried out, the category corresponding to the advertisement data to be implanted is obtained firstly, then the category is compared with the scene label corresponding to each scene to judge whether the scene label is suitable to be integrated into the scene or not, and if the scene label is suitable, the mapping relation is established between the advertisement data to be implanted and the scene label.
In one embodiment, the specific determination method is, for example: the method comprises the steps of collecting a large number of video resource scene image samples in advance, identifying attributes (scene labels) and classification labels (advertisement category implantation) of the image samples to construct a plurality of groups of data sets, constructing a classifier (such as a naive Bayes classifier), dividing the data sets into a training set and a verification set, training the classifier through the training set and verifying training results by utilizing the verification set. And after the category corresponding to the advertisement data to be implanted is obtained, inputting the category into a classifier to calculate a corresponding classification label and outputting the classification label.
In one embodiment, the scene applicability determination is performed by an empirical determination method, for example, it is determined whether the entity object or the advertisement entity corresponding to the advertisement data to be implanted frequently exists in the scene, and if so, it is determined that the scene is suitable for being merged into.
And S16, traversing each scene frame by frame according to the scene sequence to search an image block suitable for implantation, and extracting a matched advertisement image from the corresponding advertisement data to be implanted to implant the advertisement image in the image block.
According to the difference of image characteristics (size, shape, color, and the like), each advertisement data is preset with a plurality of advertisement images, and when each scene passes frame by frame according to the scene sequence, image elements on each frame of image are identified to search for an image block suitable for implantation, it should be noted that the implantation in this embodiment includes direct implantation and image element replacement (for example, a currently mature depth synthesis technology is adopted); after the image block suitable for implantation is found, the advertisement image corresponding to the advertisement data to be implanted is synthesized into the image block through an image synthesis technology, and the synthesized image is optimized so that the effect of the implanted advertisement is more vivid. Based on this, when the user views the picture, the user can view the implanted advertisement on the picture.
Specifically, through the implementation of the embodiment, a user portrait label model is constructed, corresponding products are matched in a product database according to product preference model labels, an advertisement database corresponding to video resources is accessed when a video resource access request of a user end is monitored, corresponding advertisement delivery data matching is performed in the advertisement database, the matched advertisement delivery data is determined as advertisement data to be implanted, scene traversal is performed on the current video resources to perform scene applicability judgment on the advertisement data to be implanted, each scene is traversed frame by frame according to a scene sequence to search an image block suitable for implantation, and a matched advertisement image is extracted from the corresponding advertisement data to be implanted in the image block; therefore, the advertisements which are in accordance with the user figures can be implanted into the accessed video resources according to the video resource access requests of different users, different advertisement implantation effects are generated aiming at the access of different video resources, and the accurate and instant implantation of the advertisements is realized.
Example two
Referring to fig. 2 and 5, on the basis of the first embodiment, the method of the present embodiment includes the following steps:
s20, obtaining products to be purchased of the user side 507 in the E-commerce platform, wherein the products to be purchased comprise shopping cart products and collection products.
S21, matching corresponding advertisement putting data in the advertisement database 509 according to the product to be purchased, and determining the matched advertisement putting data as the advertisement data to be implanted when a matching result exists.
When the products to be purchased in the e-commerce platform of the user end 507 are obtained, after the shopping cart products and the collected products are obtained, the purchase state of the products is verified, that is, whether the products are in an unpurchased state is verified by further obtaining historical order information, and if the products are in the unpurchased state, the products are verified to be the products to be purchased. Preferably, when a plurality of products to be purchased are available, access data (access duration and access times) corresponding to each product to be purchased are respectively acquired, and priority ranking is performed on each product to be purchased according to the access data.
Wherein, when matching the corresponding advertisement delivery data in the advertisement database 509 according to the products to be purchased, the matching is performed in sequence according to the priority order of the products to be purchased; similarly, the matching process is to identify the product category to which the advertisement delivery data belongs and compare the product category with the product to be purchased, and if the comparison is successful, the matched advertisement delivery data is determined as the advertisement data to be implanted. After that, the steps S14 to S16 will be continued.
If the comparison is unsuccessful, i.e. there is no matching result, i.e. there is no advertisement data in the advertisement database 509 that matches the advertisement data to be implanted corresponding to the product to be purchased, the method further comprises the following steps:
s30, acquiring advertisement enrollment requirements of the video resource end 508 and advertisement putting data of the product to be purchased, wherein the advertisement enrollment requirements at least comprise charging information, and the advertisement putting data at least comprise budget information.
And S31, judging whether the advertisement putting data of the product to be purchased meet the advertisement enrollment requirement.
And if so, the process goes to S32, an advertisement putting contract is automatically performed on the product to be purchased and the video resource end 508, and the advertisement putting data of the product to be purchased is determined as the advertisement data to be implanted.
Wherein the user end 507 sends an advertisement enrollment requirement acquisition request to the video resource end 508 to acquire an advertisement enrollment requirement of the video resource end 508; according to one implementation mode, a crawler tool is adopted to obtain advertisement putting data corresponding to products to be purchased on the Internet; in another embodiment, an intermediate server is constructed in advance, and clients upload advertisement delivery data corresponding to respective products to the intermediate server; and searching in the intermediate server to obtain the advertisement putting data corresponding to the product to be purchased. The ad enrollment need, i.e., the ad enrollment condition, may limit other conditions such as product category, market size, etc., in addition to the charging information. And judging whether the advertisement putting data of the product to be purchased meets the advertisement putting requirement or not, namely whether the advertisement putting data is matched with the corresponding condition or not, if so, automatically carrying out advertisement putting contract on the product to be purchased and the video resource end 508, and determining the advertisement putting data of the product to be purchased as the advertisement data to be implanted. After that, the steps S14 to S16 will be continued.
Based on the implementation of the embodiment, the video resource access requests of different users can implant advertisements meeting the actual purchase requirements of the accessed video resources, so that the advertisement implanting range is widened.
EXAMPLE III
Referring to fig. 3 and 5, on the basis of the first embodiment, the method of the present embodiment includes the following steps:
and S40, performing barrage traversal on each scene to sort the barrage quantity.
And S41, traversing each scene frame by frame according to the bullet screen amount sequence to search image blocks suitable for implantation.
Specifically, after traversing all scenes in the video resource, the user side 507 further obtains the bullet screen amount (the number of bullet screens or the total number of words of bullet screens) in the corresponding time period of each scene, and then sorts the scenes according to the bullet screen amount; and traversing each scene frame by frame according to the bullet screen quantity sequencing result to search an image block suitable for implantation (preferentially traversing scenes with the bullet screen quantity ranked at the top frame by frame), and during the traversal of each scene frame by frame, identifying image elements on each frame of picture to search an image block suitable for implantation so as to facilitate the subsequent advertisement implantation.
Based on the implementation of this embodiment, can be preferentially carry out advertisement implantation to the scene that bullet screen volume leaned on the front to promote advertisement implantation's marketing effect.
Example four
Referring to fig. 5, a system 50 for user profile based advertisement placement on the fly, said system 50 comprising:
a tag model building module 501, configured to build a user portrait tag model 502 according to user behavior data, where the user portrait tag model 502 at least includes a product preference model tag.
A product matching module 503, configured to match corresponding products in the product database 504 according to the product preference model labels.
An index creation module 505 for creating a product index according to the product category.
A database access module 506, configured to send a database access request to the video resource source 508 when a video resource access request of the user end 507 is monitored, so as to access the advertisement database 509 corresponding to the video resource.
A first advertisement matching module 510, configured to perform corresponding advertisement delivery data matching in the advertisement database 509 according to the product index, and determine the matched advertisement delivery data as advertisement data to be implanted.
A scene traversal module 511, configured to perform scene traversal on the current video resource to generate a scene tag.
A scene applicability judging module 512, configured to perform scene applicability judgment on the advertisement data to be implanted.
A mapping relationship establishing module 513, configured to establish a mapping relationship between the scene tag and the advertisement data to be implanted according to a result of determining that the scene is suitable for the advertisement data to be implanted.
A first image block searching module 514, configured to traverse each scene frame by frame according to the scene order to search for an image block suitable for implantation.
And an advertisement implanting module 515, configured to extract a matching advertisement image from the corresponding advertisement data to be implanted for implanting in the image block.
In one embodiment, the system further comprises:
a to-be-purchased product obtaining module 516, configured to obtain a to-be-purchased product in the e-commerce platform at the user end 507, where the to-be-purchased product includes a shopping cart product and a collection product.
The second advertisement matching module 517 is configured to perform corresponding advertisement delivery data matching in the advertisement database 509 according to the product to be purchased, and determine the matched advertisement delivery data as advertisement data to be implanted when a matching result exists.
In one embodiment, the system further comprises:
a data obtaining module 518, configured to obtain an advertisement enrollment demand of the video resource end 508 and advertisement delivery data of the product to be purchased when there is no matching result when corresponding advertisement delivery data matching is performed in the advertisement database 509 according to the product to be purchased, where the advertisement enrollment demand at least includes charging information, and the advertisement delivery data at least includes budget information.
And a enrollment requirement determining module 519, configured to determine whether the advertisement delivery data of the product to be purchased meets the advertisement enrollment requirement.
And an advertisement signing module 520, configured to, when the advertisement delivery data of the product to be purchased meets the advertisement posting requirement, automatically perform advertisement delivery signing on the product to be purchased and the video resource source 508, and determine the advertisement delivery data of the product to be purchased as advertisement data to be implanted.
In one embodiment, the system further comprises:
and the bullet screen traversing module 521 is configured to perform bullet screen traversal on each scene to sort bullet screen amounts.
And the second image block searching module 522 is configured to traverse each scene frame by frame according to the bullet screen amount sorting to search an image block suitable for implantation.
In some embodiments, and as shown in FIG. 6, an advertisement instant placement device 60 based on user profile is provided, comprising: a memory 601 and a processor 602, wherein the memory 601 is used for storing a computer program, and the processor 602 is used for calling the computer program to execute the corresponding steps of the user portrait based advertisement immediate implantation method provided by the embodiment.
In some embodiments, a computer-readable storage medium 70 is provided, in which a computer program is stored in the computer-readable storage medium 70, and when the computer program runs on a computer, the computer program performs the corresponding steps of a user representation-based advertisement immediate placement method provided by this embodiment.
Referring to FIG. 7, a computer readable storage medium 70 includes a computer program for executing a computer process on a computing device.
In some embodiments, the computer-readable storage medium 70 is provided using a signal bearing medium 700. The signal bearing medium 700 may include one or more program instructions that, when executed by one or more processors, may provide the functions or portions of the functions described above with respect to fig. 1. Thus, for example, one or more features of a user representation-based advertisement instant placement method may be undertaken by one or more instructions associated with the signal bearing medium 700. Further, the program instructions in FIG. 7 also describe example instructions. In some examples, signal bearing medium 700 may comprise a computer readable medium 701, such as, but not limited to, a hard disk drive, a Compact Disc (CD), a Digital Video Disc (DVD), a digital tape, a memory, a read-only memory (ROM), a random-access memory (RAM), or the like.
In some implementations, the signal bearing medium 700 may comprise a computer recordable medium 702 such as, but not limited to, a memory, a read/write (R/W) CD, a R/WDVD, and so forth.
In some implementations, the signal bearing medium 700 may include a communication medium 703, such as, but not limited to, a digital and/or analog communication medium (e.g., a fiber optic cable, a waveguide, a wired communications link, a wireless communication link, etc.).
The signal bearing medium 700 may be conveyed by a wireless form of communication medium 703, such as a wireless communication medium conforming to the IEEE802.11 standard or other transmission protocol. The one or more program instructions may be, for example, computer-executable instructions or logic-implementing instructions.
It should be understood that the arrangements described herein are for illustrative purposes only. Thus, those skilled in the art will appreciate that other arrangements and other elements (e.g., machines, interfaces, functions, orders, and groupings of functions, etc.) can be used instead, and that some elements may be omitted altogether depending upon the desired results. In addition, many of the described elements are functional entities that may be implemented as discrete or distributed components or in conjunction with other components, in any suitable combination and location.
In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method for instantly implanting an advertisement based on a user profile, the method comprising the steps of:
constructing a user portrait label model according to user behavior data, wherein the user portrait label model at least comprises a product preference model label;
matching corresponding products in a product database according to the product preference model labels and creating product indexes according to product categories;
when monitoring a video resource access request of a user side, sending a database access request to the video resource side to access an advertisement database corresponding to the video resource;
performing corresponding advertisement putting data matching in the advertisement database according to the product index and determining the matched advertisement putting data as advertisement data to be implanted;
performing scene traversal on the current video resource to generate a scene label, performing scene applicability judgment on the advertisement data to be implanted, and establishing a mapping relation between the scene label and the advertisement data to be implanted according to a judgment result;
and traversing each scene frame by frame according to the sequence of the scenes to search for image blocks suitable for implantation, and extracting matched advertisement images from the corresponding advertisement data to be implanted to implant the advertisement images into the image blocks.
2. The method of claim 1, wherein the method further comprises the steps of:
acquiring products to be purchased of a user side in an e-commerce platform, wherein the products to be purchased comprise shopping cart products and collected products;
and matching corresponding advertisement putting data in the advertisement database according to the product to be purchased, and determining the matched advertisement putting data as the advertisement data to be implanted when a matching result exists.
3. The method of claim 2, wherein if there is no match, the method further comprises:
acquiring advertisement enrollment requirements of the video resource end and advertisement release data of the product to be purchased, wherein the advertisement enrollment requirements at least comprise charging information, and the advertisement release data at least comprise budget information;
judging whether the advertisement putting data of the product to be purchased meet the advertisement enrollment requirement or not;
and if the advertisement data meets the preset requirement, automatically performing advertisement putting subscription on the product to be purchased and the video resource end, and determining the advertisement putting data of the product to be purchased as the advertisement data to be implanted.
4. The method of claim 2, wherein the method further comprises the steps of:
performing bullet screen traversal on each scene to sequence bullet screen quantities;
and traversing each scene frame by frame according to the bullet screen amount sequencing to search image blocks suitable for implantation.
5. A user profile based advertisement placement system, the system comprising:
the tag model building module is used for building a user portrait tag model according to user behavior data, wherein the user portrait tag model at least comprises a product preference model tag;
the product matching module is used for matching corresponding products in a product database according to the product preference model labels;
the index creating module is used for creating a product index according to the product category;
the database access module is used for sending a database access request to the video resource end to access an advertisement database corresponding to the video resource when monitoring a video resource access request of a user end;
the first advertisement matching module is used for matching corresponding advertisement putting data in the advertisement database according to the product index and determining the matched advertisement putting data as advertisement data to be implanted;
the scene traversal module is used for performing scene traversal on the current video resource to generate a scene label;
the scene applicability judging module is used for carrying out scene applicability judgment on the advertisement data to be implanted;
the mapping relation establishing module is used for establishing the mapping relation between the scene label and the advertisement data to be implanted according to the result of judging the scene applicability of the advertisement data to be implanted;
the first image block searching module is used for traversing each scene frame by frame according to the scene sequence to search an image block suitable for implantation;
and the advertisement implanting module is used for extracting a matched advertisement image from the corresponding advertisement data to be implanted so as to implant the advertisement image into the image block.
6. The user representation based advertisement placement system of claim 5, further comprising:
the system comprises a to-be-purchased product acquisition module, a to-be-purchased product acquisition module and a to-be-purchased product acquisition module, wherein the to-be-purchased products comprise shopping cart products and collected products;
and the second advertisement matching module is used for matching corresponding advertisement putting data in the advertisement database according to the product to be purchased and determining the matched advertisement putting data as the advertisement data to be implanted when a matching result exists.
7. The user representation based advertisement placement system of claim 6, further comprising:
the data acquisition module is used for acquiring the advertising enrollment demand of the video resource end and the advertising data of the product to be purchased when no matching result exists when corresponding advertising data matching is carried out in the advertising database according to the product to be purchased, wherein the advertising enrollment demand at least comprises charging information, and the advertising data at least comprises budget information;
the enrollment requirement judging module is used for judging whether the advertisement putting data of the product to be purchased meet the advertisement enrollment requirement or not;
and the advertisement signing module is used for automatically carrying out advertisement putting signing on the product to be purchased and the video resource end when the advertisement putting data of the product to be purchased meet the advertisement putting demand, and determining the advertisement putting data of the product to be purchased as the advertisement data to be implanted.
8. The user representation based advertisement placement system of claim 6, further comprising:
the bullet screen traversal module is used for performing bullet screen traversal on each scene so as to sequence bullet screen quantities;
and the second image block searching module is used for traversing each scene frame by frame according to the bullet screen amount sequence so as to search the image block suitable for implantation.
9. An advertisement instant placement device based on user profile, comprising: a memory for storing a computer program and a processor for invoking the computer program to perform the method of any of claims 1-4.
10. A computer-readable storage medium, in which a computer program is stored which, when run on a computer, causes the computer to carry out the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210824245.0A CN115187301A (en) | 2022-07-14 | 2022-07-14 | Advertisement instant implanting method, system and device based on user portrait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210824245.0A CN115187301A (en) | 2022-07-14 | 2022-07-14 | Advertisement instant implanting method, system and device based on user portrait |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115187301A true CN115187301A (en) | 2022-10-14 |
Family
ID=83519173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210824245.0A Pending CN115187301A (en) | 2022-07-14 | 2022-07-14 | Advertisement instant implanting method, system and device based on user portrait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115187301A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116308530A (en) * | 2023-05-16 | 2023-06-23 | 飞狐信息技术（天津）有限公司 | Advertisement implantation method, advertisement implantation device, advertisement implantation equipment and readable storage medium |
| CN117291670A (en) * | 2023-09-14 | 2023-12-26 | 广州太棒了传媒科技有限公司 | Video advertisement playing method and device based on crowd data |
-
2022
- 2022-07-14 CN CN202210824245.0A patent/CN115187301A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116308530A (en) * | 2023-05-16 | 2023-06-23 | 飞狐信息技术（天津）有限公司 | Advertisement implantation method, advertisement implantation device, advertisement implantation equipment and readable storage medium |
| CN117291670A (en) * | 2023-09-14 | 2023-12-26 | 广州太棒了传媒科技有限公司 | Video advertisement playing method and device based on crowd data |
| CN117291670B (en) * | 2023-09-14 | 2024-04-05 | 广州太棒了传媒科技有限公司 | Video advertisement playing method and device based on crowd data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10735494B2 (en) | Media information presentation method, client, and server | |
| CN108829764B (en) | Recommendation information acquisition method, device, system, server and storage medium | |
| US11620678B2 (en) | Advertising method, device and system, and computer-readable storage medium | |
| JP6821149B2 (en) | Information processing using video for advertisement distribution | |
| JP6827515B2 (en) | Viewing time clustering for video search | |
| US9711182B2 (en) | System and method for identifying and altering images in a digital video | |
| CN115187301A (en) | Advertisement instant implanting method, system and device based on user portrait | |
| US20150215605A1 (en) | Virtual advertising platform | |
| US20130247083A1 (en) | Systems and methods for matching an advertisement to a video | |
| KR101385700B1 (en) | Method and apparatus for providing moving image advertisements | |
| CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
| US11729478B2 (en) | System and method for algorithmic editing of video content | |
| WO2008033840A2 (en) | System and methods for creating, collecting, and using metadata | |
| CN113010701A (en) | Video-centered fused media content recommendation method and device | |
| CN108476344A (en) | The content selection of networked media device | |
| WO2013030634A1 (en) | Virtual advertising platform | |
| US20150131967A1 (en) | Computerized systems and methods for generating models for identifying thumbnail images to promote videos | |
| CN111259245B (en) | Work pushing method, device and storage medium | |
| KR101966596B1 (en) | Contents processing type marketing system based on SNS, and method thereof | |
| KR102232921B1 (en) | After Product Placement advertising provision system | |
| CN108416645B (en) | Recommendation method, device, storage medium and equipment for user | |
| WO2022126064A1 (en) | Virtual product placement | |
| US20150227970A1 (en) | System and method for providing movie file embedded with advertisement movie | |
| KR20200133300A (en) | Social media-based contents processing marketing system and method | |
| US20180350052A1 (en) | Method and system for analyzing test image |
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 |